SwePub - sökning: hsv:(NATURVETENSKAP) hsv:(Data...

Numrering	Referens	Omslagsbild	Hitta
1.	Wilhelmsson, Kenneth, 1976 (författare) Huvudansatser för parsningsmetoder. Om programutvecklingens förutsättningar i en svensk kontext 2016 Rapport (övrigt vetenskapligt/konstnärligt)abstract Syftet med denna text var att ge en inblick i området (syntaktisk) parsning. Tanken var att ge en bild av utvecklingen som var 1) fri från alltför tekniska detaljer, då området är programmeringstekniskt, och 2) beskriven ur ett svenskt perspektiv. Bakgrunden till valet av ämne till texten, som var tänkt att finnas med i antologin Text och kontext, var att parsning är relativt okänt för många personer verksamma inom närliggande områden, samtidigt som det är ett absolut nyckelbegrepp för den som ägnar sig åt datorlingvistik eller språkteknologi. Målet var alltså att ge en ganska allmän utifrånblick på några centrala sidor av utvecklingen, samtidigt som det tydligt är så att den som själv arbetat med utveckling kan ha starka åsikter och preferenser rörande metodval, något som i ärlighetens namn kanske inte heller denna text är lösgjord från. Hur ska det göras? Konsten att utveckla automatisk syntaxanalys av naturlig text kan läras ut från ett flertal perspektiv. Det kan t.ex. ske med fokus på användandet av en viss grammatikformalism, med fokus på beräkningssnabbhet, med fokus på entydiggörande av möjliga ambiguiteter. Tolkningsval kan göras med hjälp av antingen handskrivna regler eller inhämtad statistik. En sorts huvudtema i denna text är hur metoder för parsning på senare år uppvisar förändringar som kanske kan förklaras med att programmen har fått andra användningsområden och att metoderna har anpassats därefter (en annan tolkning är att flera senare system inte längre gör parsning i strikt mening). När detta tänkta ”kapitel” var färdigt fick det kommentaren att det inte var anpassat för antologins målgrupp. Det fick skrivas en annan kapiteltext, men det kom samtidigt ett förslag att publicera texten om parsning här som denna rapport.
2.	Wilhelmsson, Kenneth, 1976 (författare) Autentiska och artificiella frågor till svensk text Automatisk frågegenerering jämfört med användares frågor för informationsåtkomst : Authentic and artificial questions to Swedish text Automatically generated questions versus user-generated questions for information access 2015 Annan publikation (övrigt vetenskapligt/konstnärligt)abstract Informationssökning mot ostrukturerade datakällor som fri text är ett av de områden där användargränssnitt med fri formulering i naturligt språk har tagits fram. I ett sådant, eventuellt AI-betonat, system kan några grundläggande svårigheter från användarperspektivet märkas. En sådan svårighet är att en användare inte känner till huruvida en fråga som hon avser att ställa egentligen kan besvaras av den aktuella texten. Denna svårighet, tillsammans med andra, som de kraftiga variationsmöjligheterna för formen för ett giltigt svar på en ställd fråga, riskerar att leda till att användarintrycken av systemtypen blir negativa. De moment som behöver ingå i ett sådant frågebaserat informationssystems funktionssätt måste på något sätt inbegripa en mappning av frågeled i frågan (t.ex. när) till den form och grammatisk funktion som svaret i texten måste ha (för frågan när normalt ett tidsadverbial). Bland annat denna iakttagelse inbjuder till användning av automatisk frågegenerering (question generation, QG). Frågegenerering innebär att frågor som en naturlig text besvarar initialt utvinns av ett program som samlar in dem i explicit form. Tanken för användning i informationssökning är att en användare i gränssnittet enbart ska kunna ställa just dessa frågor, vilka faktiskt besvaras av texten. Denna studie gäller just de frågor som ett automatiskt frågegenereringssystem för svenska kan, och genom vidare utveckling, skulle kunna generera för godtycklig digital svensk text. Även om mängden automatiskt genererade frågor och frågeformuleringar kan bli mycket stor, utrymmesmässigt många gånger större än ursprungstexten, så är det tydligt att den beskrivna metoden för frågegenerering för svenska inte kan och troligen inte heller kommer att kunna förmås att skapa alla de frågor och frågeformuleringar som en vanlig användare skulle anse att en viss text besvarar. Men hur väl fungerar då automatiskt genererade frågor i detta sammanhang? Denna uppsats kretsar kring en användarundersökning där undersökningsdeltagare har ombetts att formulera frågor som texter besvarar, och som anses vara relevanta frågor. Den resulterande samlingen frågor undersöktes och kategoriserades. Resultatet av undersökningens huvudfråga visar att bara 20-25 % av användarnas frågeformuleringar skulle kunna genereras direkt automatiskt med aktuell ansats – utan vissa informationstekniska förbättringar. Uppsatsen föreslår viss ny terminologi för detta outforskade område, bl.a. för att skilja mellan de olika grader av processkrav som generering av olika frågeslag från text kräver.
3.	Ellison, Magnus, et al. (författare) En implementation för domänoberoende textkategorisering 2001 Annan publikation (övrigt vetenskapligt/konstnärligt)
4.	Norlund, Tobias, 1991, et al. (författare) Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it? 2021 Ingår i: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pp. 149-162, Punta Cana, Dominican Republic. - : Association for Computational Linguistics. Konferensbidrag (refereegranskat)abstract Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provide the model with additional data modalities that complements the knowledge obtained through text. We investigate the use of visual data to complement the knowledge of large language models by proposing a method for evaluating visual knowledge transfer to text for uni- or multimodal language models. The method is based on two steps, 1) a novel task querying for knowledge of memory colors, i.e. typical colors of well-known objects, and 2) filtering of model training data to clearly separate knowledge contributions. Additionally, we introduce a model architecture that involves a visual imagination step and evaluate it with our proposed method. We find that our method can successfully be used to measure visual knowledge transfer capabilities in models and that our novel model architecture shows promising results for leveraging multimodal knowledge in a unimodal setting.
5.	Yun, Yixiao, 1987, et al. (författare) Maximum-Likelihood Object Tracking from Multi-View Video by Combining Homography and Epipolar Constraints 2012 Ingår i: 6th ACM/IEEE Int'l Conf on Distributed Smart Cameras (ICDSC 12), Oct 30 - Nov.2, 2012, Hong Kong. - 9781450317726 ; , s. 6 pages- Konferensbidrag (refereegranskat)abstract This paper addresses problem of object tracking in occlusion scenarios, where multiple uncalibrated cameras with overlapping fields of view are used. We propose a novel method where tracking is first done independently for each view and then tracking results are mapped between each pair of views to improve the tracking in individual views, under the assumptions that objects are not occluded in all views and move uprightly on a planar ground which may induce a homography relation between each pair of views. The tracking results are mapped by jointly exploiting the geometric constraints of homography, epipolar and vertical vanishing point. Main contributions of this paper include: (a) formulate a reference model of multi-view object appearance using region covariance for each view; (b) define a likelihood measure based on geodesics on a Riemannian manifold that is consistent with the destination view by mapping both the estimated positions and appearances of tracked object from other views; (c) locate object in each individual view based on maximum likelihood criterion from multi-view estimations of object position. Experiments have been conducted on videos from multiple uncalibrated cameras, where targets experience long-term partial or full occlusions. Comparison with two existing methods and performance evaluations are also made. Test results have shown effectiveness of the proposed method in terms of robustness against tracking drifts caused by occlusions.
6.	Wilhelmsson, Kenneth, 1976 (författare) Om förutsättningarna för språkligt datorstöd på ordnivån och uppåt 2017 Ingår i: Text och kontext - perspektiv på textanalys / Karin Helgesson, Hans Lundqvist, Anna Lyngfelt, Andreas Nord & Åsa Wengelin (red.). - Malmö : Gleerups. - 9789140693648 ; , s. 207-228 Bokkapitel (övrigt vetenskapligt/konstnärligt)
7.	Al Sabbagh, Khaled, 1987, et al. (författare) Improving Data Quality for Regression Test Selection by Reducing Annotation Noise 2020 Ingår i: Proceedings - 46th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2020. ; , s. 191-194 Konferensbidrag (refereegranskat)abstract Big data and machine learning models have been increasingly used to support software engineering processes and practices. One example is the use of machine learning models to improve test case selection in continuous integration. However, one of the challenges in building such models is the identification and reduction of noise that often comes in large data. In this paper, we present a noise reduction approach that deals with the problem of contradictory training entries. We empirically evaluate the effectiveness of the approach in the context of selective regression testing. For this purpose, we use a curated training set as input to a tree-based machine learning ensemble and compare the classification precision, recall, and f-score against a non-curated set. Our study shows that using the noise reduction approach on the training instances gives better results in prediction with an improvement of 37% on precision, 70% on recall, and 59% on f-score.
8.	Ferro, Nicola, et al. (författare) PROMISE Retreat Report Prospects and Opportunities for Information Access Evaluation 2013 Ingår i: ACM SIGIR Forum. - : Association for Computing Machinery (ACM). - 0163-5840 .- 1558-0229. ; 46:2, s. 60-84 Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract The PROMISE network of excellence organized a two-days brainstorming workshop on 30th and 31st May 2012 in Padua, Italy, to discuss and envisage future directions and perspectives for the evaluation of information access and retrieval systems in multiple languages and multiple media. This document reports on the outcomes of this event and provides details about the six envisaged research lines: search applications; contextual evaluation; challenges in test collection design and exploitation; component-based evaluation; ongoing evaluation; and signal-aware evaluation. The ultimate goal of the PROMISE retreat is to stimulate and involve the research community along these research lines and to provide funding agencies with effective and scientifically sound ideas for coordinating and supporting information access research.
9.	Samoaa, Hazem Peter, et al. (författare) A systematic mapping study of source code representation for deep learning in software engineering 2022 Ingår i: Iet Software. - : Institution of Engineering and Technology (IET). - 1751-8806 .- 1751-8814. ; 16:4, s. 351-385 Tidskriftsartikel (refereegranskat)abstract The usage of deep learning (DL) approaches for software engineering has attracted much attention, particularly in source code modelling and analysis. However, in order to use DL, source code needs to be formatted to fit the expected input form of DL models. This problem is known as source code representation. Source code can be represented via different approaches, most importantly, the tree-based, token-based, and graph-based approaches. We use a systematic mapping study to investigate i detail the representation approaches adopted in 103 studies that use DL in the context of software engineering. Thus, studies are collected from 2014 to 2021 from 14 different journals and 27 conferences. We show that each way of representing source code can provide a different, yet orthogonal view of the same source code. Thus, different software engineering tasks might require different (combinations of) code representation approaches, depending on the nature and complexity of the task. Particularly, we show that it is crucial to define whether the DL approach requires lexical, syntactical, or semantic code information. Our analysis shows that a wide range of different representations and combinations of representations (hybrid representations) are used to solve a wide range of common software engineering problems. However, we also observe that current research does not generally attempt to transfer existing representations or models to other studies even though there are other contexts in which these representations and models may also be useful. We believe that there is potential for more reuse and the application of transfer learning when applying DL to software engineering tasks.
10.	Huhnstock, Nikolas Alexander, 1988-, et al. (författare) An Infinite Replicated Softmax Model for Topic Modeling 2019 Ingår i: Modeling Decisions for Artificial Intelligence. - Cham : Springer. - 9783030267728 - 9783030267735 ; , s. 307-318 Konferensbidrag (refereegranskat)abstract In this paper, we describe the infinite replicated Softmax model (iRSM) as an adaptive topic model, utilizing the combination of the infinite restricted Boltzmann machine (iRBM) and the replicated Softmax model (RSM). In our approach, the iRBM extends the RBM by enabling its hidden layer to adapt to the data at hand, while the RSM allows for modeling low-dimensional latent semantic representation from a corpus. The combination of the two results is a method that is able to self-adapt to the number of topics within the document corpus and hence, renders manual identification of the correct number of topics superfluous. We propose a hybrid training approach to effectively improve the performance of the iRSM. An empirical evaluation is performed on a standard data set and the results are compared to the results of a baseline topic model. The results show that the iRSM adapts its hidden layer size to the data and when trained in the proposed hybrid manner outperforms the base RSM model.
11.	Kucher, Kostiantyn, et al. (författare) Visual Analysis of Online Social Media to Open Up the Investigation of Stance Phenomena 2016 Ingår i: Information Visualization. - : Sage Publications. - 1473-8716 .- 1473-8724. ; 15:2, s. 93-116 Tidskriftsartikel (refereegranskat)abstract Online social media are a perfect text source for stance analysis. Stance in human communication is concerned with speaker attitudes, beliefs, feelings and opinions. Expressions of stance are associated with the speakers' view of what they are talking about and what is up for discussion and negotiation in the intersubjective exchange. Taking stance is thus crucial for the social construction of meaning. Increased knowledge of stance can be useful for many application fields such as business intelligence, security analytics, or social media monitoring. In order to process large amounts of text data for stance analyses, linguists need interactive tools to explore the textual sources as well as the processed data based on computational linguistics techniques. Both original texts and derived data are important for refining the analyses iteratively. In this work, we present a visual analytics tool for online social media text data that can be used to open up the investigation of stance phenomena. Our approach complements traditional linguistic analysis techniques and is based on the analysis of utterances associated with two stance categories: sentiment and certainty. Our contributions include (1) the description of a novel web-based solution for analyzing the use and patterns of stance meanings and expressions in human communication over time; and (2) specialized techniques used for visualizing analysis provenance and corpus overview/navigation. We demonstrate our approach by means of text media on a highly controversial scandal with regard to expressions of anger and provide an expert review from linguists who have been using our tool.
12.	Dobnik, Simon, 1977 (författare) Coordinating spatial perspective in discourse 2012 Ingår i: Proceedings of the Workshop on Vision and Language 2012 (VL'12): The 2nd Annual Meeting of the EPSRC Network on Vision and Language. Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract We present results of an on-line data collection experiment where we investigate the assignment and coordination of spatial perspective between a pair of dialogue participants situated in a constrained virtual environment.
13.	Barreiro, Anabela, et al. (författare) Multi3Generation : Multitask, Multilingual, Multimodal Language Generation 2022 Ingår i: Proceedings of the 23rd Annual Conference of the European Association for Machine Translation. - : European Association for Machine Translation. ; , s. 345-346 Konferensbidrag (refereegranskat)abstract This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generatio(CA18231), an interdisciplinary networof research groups working on different aspects of language generation. This "meta-paper" will serve as reference for citationof the Action in future publications. It presents the objectives, challenges and a the links for the achieved outcomes.
14.	Amundin, Mats, et al. (författare) A proposal to use distributional models to analyse dolphin vocalisation 2017 Ingår i: Proceedings of the 1st International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, VIHAR 2017. - 9782956202905 ; , s. 31-32 Konferensbidrag (refereegranskat)abstract This paper gives a brief introduction to the starting points of an experimental project to study dolphin communicative behaviour using distributional semantics, with methods implemented for the large scale study of human language.
15.	Lindgren, Helena, Professor, et al. (författare) The wasp-ed AI curriculum : A holistic curriculum for artificial intelligence 2023 Ingår i: INTED2023 Proceedings. - : IATED. - 9788409490264 ; , s. 6496-6502 Konferensbidrag (refereegranskat)abstract Efforts in lifelong learning and competence development in Artificial Intelligence (AI) have been on the rise for several years. These initiatives have mostly been applied to Science, Technology, Engineering and Mathematics (STEM) disciplines. Even though there has been significant development in Digital Humanities to incorporate AI methods and tools in higher education, the potential for such competences in Arts, Humanities and Social Sciences is far from being realised. Furthermore, there is an increasing awareness that the STEM disciplines need to include competences relating to AI in humanity and society. This is especially important considering the widening and deepening of the impact of AI on society at large and individuals. The aim of the presented work is to provide a broad and inclusive AI Curriculum that covers the breadth of the topic as it is seen today, which is significantly different from only a decade ago. It is important to note that with the curriculum we mean an overview of the subject itself, rather than a particular education program. The curriculum is intended to be used as a foundation for educational activities in AI to for example harmonize terminology, compare different programs, and identify educational gaps to be filled. An important aspect of the curriculum is the ethical, legal, and societal aspects of AI and to not limit the curriculum to the STEM subjects, instead extending to a holistic, human-centred AI perspective. The curriculum is developed as part of the national research program WASP-ED, the Wallenberg AI and transformative technologies education development program.
16.	Singh, Avinash, 1986-, et al. (författare) Verbal explanations by collaborating robot teams 2021 Ingår i: Paladyn - Journal of Behavioral Robotics. - : De Gruyter Open. - 2080-9778 .- 2081-4836. ; 12:1, s. 47-57 Tidskriftsartikel (refereegranskat)abstract In this article, we present work on collaborating robot teams that use verbal explanations of their actions and intentions in order to be more understandable to the human. For this, we introduce a mechanism that determines what information the robots should verbalize in accordance with Grice’s maxim of quantity, i.e., convey as much information as is required and no more or less. Our setup is a robot team collaborating to achieve a common goal while explaining in natural language what they are currently doing and what they intend to do. The proposed approach is implemented on three Pepper robots moving objects on a table. It is evaluated by human subjects answering a range of questions about the robots’ explanations, which are generated using either our proposed approach or two further approaches implemented for evaluation purposes. Overall, we find that our proposed approach leads to the most understanding of what the robots are doing. In addition, we further propose a method for incorporating policies driving the distribution of tasks among the robots, which may further support understandability.
17.	Ryazanov, Igor, et al. (författare) Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences 2021 Ingår i: Journal of Marine Science and Engineering. - : MDPI AG. - 2077-1312. ; 9:2 Tidskriftsartikel (refereegranskat)abstract Driven by the unprecedented availability of data, machine learning has become a pervasive and transformative technology across industry and science. Its importance to marine science has been codified as one goal of the UN Ocean Decade. While increasing amounts of, for example, acoustic marine data are collected for research and monitoring purposes, and machine learning methods can achieve automatic processing and analysis of acoustic data, they require large training datasets annotated or labelled by experts. Consequently, addressing the relative scarcity of labelled data is, besides increasing data analysis and processing capacities, one of the main thrust areas. One approach to address label scarcity is the expert-in-the-loop approach which allows analysis of limited and unbalanced data efficiently. Its advantages are demonstrated with our novel deep learning-based expert-in-the-loop framework for automatic detection of turbulent wake signatures in echo sounder data. Using machine learning algorithms, such as the one presented in this study, greatly increases the capacity to analyse large amounts of acoustic data. It would be a first step in realising the full potential of the increasing amount of acoustic data in marine sciences.
18.	Proceedings of the workshop on Nordic language research infrastructure at NODALIDA 2013, May 22-24, 2013, Oslo, Norway : NEALT Proceedings Series 20 2013 Samlingsverk (redaktörskap) (övrigt vetenskapligt/konstnärligt)
19.	Höglund, Lars, 1946, et al. (författare) Maskininlärningsbaserad indexering av digitaliserade museiartefakter - projektrapport 2012 Rapport (övrigt vetenskapligt/konstnärligt)abstract Projektet har genomfört försök med maskinbaserad analys och maskininlärning för automatisk indexering och analys av bilder som stöd för registrering av föremål i museibestånd. Resultaten visar att detta är möjligt för avgränsade delmängder i kombination med maskininlärning som stöd för, men inte som ersättning för, manuell analys. Projektet har också funnit behov av utveckling av ett användargränssnitt för både text och bildsökning och utvecklat en prototyplösning för detta, vilket finns dokumenterat i denna rapport och i ett separat appendix till rapporten. Materialet utgör grundunderlag för implementeringar som innebär utökade sökmöjligheter, effektivare registrering samt ett användarvänligt gränssnitt. Arbetet ligger i framkant av forskningsområdets resultat och etablerade metoder och kombinerar statististiska, lingvistiska och datavetenskapliga metoder. Se länk till rapport och även länk till appendix längre ned.
20.	Andersson, Niclas S, 1971, et al. (författare) Feature-Based Response Classification in Nonlinear Structural Design Simulations 2018 Ingår i: SAE International Journal of Vehicle Dynamics, Stability, and NVH. - : SAE International. - 2380-2162 .- 2380-2170. ; 2:3, s. 185-202 Tidskriftsartikel (refereegranskat)abstract An applied system design analysis approach for automated processing and classification of simulated structural responses is presented. Deterministic and nonlinear dynamics are studied under ideal loading and low noise conditions to determine fundamental system properties, how they vary and possibly interact. Using powerful computer resources, large amounts of simulated raw data can be produced in a short period of time. Efficient tools for data processing and interpretation are then needed, but existing ones often require much manual preparation and direct human judgement. Thus, there is a need to develop techniques that help to treat more virtual prototype variants and efficiently extract useful information from them. For this, time signals are evaluated by methods commonly used within structural dynamics and statistical learning. A multi-level multi-frequency stimulus function is constructed and simulated response signals are combined into frequency domain functions. These are associated with qualitative system features, such as being periodic or aperiodic, linear or nonlinear and further into subcategories of nonlinear systems, such as fundamental, sub or super harmonic and even or odd order types. Appropriate classes are then determined from selected feature metrics and rules-of-thumb criteria. To automate the classification of large data sets, a support vector machine is trained on categorised responses to determine whether a single feature, or combinations of features, applies or not. The trained classifier can then efficiently process new sets of data and pick out cases that are associated with possible vibrational problems, which subsequently can be further analysed and understood. This article describes elements of the analysis, discuss the effectiveness of evaluated feature metrics, reports practical considerations and results from two separate training study examples.
21.	Camilleri, John J., 1986, et al. (författare) Modelling and analysis of normative documents 2017 Ingår i: Journal of Logical and Algebraic Methods in Programming. - : Elsevier BV. - 2352-2208 .- 2352-2216. ; 91, s. 33-59 Tidskriftsartikel (refereegranskat)abstract We are interested in using formal methods to analyse normative documents or contracts such as terms of use, privacy policies, and service agreements. We begin by modelling such documents in terms of obligations, permissions and prohibitions of agents over actions, restricted by timing constraints and including potential penalties resulting from the non-fulfilment of clauses. This is done using the C-O Diagram formalism, which we have extended syntactically and for which we have defined a new trace semantics. Models in this formalism can then be translated into networks of timed automata, and we have a complete working implementation of this translation. The network of automata is used as a specification of a normative document, making it amenable to verification against given properties. By applying this approach to a case study from a real-world contract, we show the kinds of analysis possible through both syntactic querying on the structure of the model, as well as verification of properties using UPPAAL.
22.	Fredriksson, Teodor, 1992, et al. (författare) Machine Learning Algorithms for Labeling: Where and How They are Used? 2022 Ingår i: SysCon 2022 - 16th Annual IEEE International Systems Conference, Proceedings. Konferensbidrag (refereegranskat)abstract With the increased availability of new and better computer processing units (CPUs) as well as graphical processing units (GPUs), the interest in statistical learning and deep learning algorithms for classification tasks has grown exponentially. These classification algorithms often require the presence of fully labeled instances during the training period for maximum classification accuracy. However, in industrial applications, data is commonly not fully labeled, which both reduces the prediction accuracy of the learning algorithms as well as increases the project cost to label the missing instances. The purpose of this paper is to survey the current state-of-the-art literature on machine learning algorithms that are used for assisted or automatic labeling and to understand where these are used. We performed a systematic mapping study and identified 52 primary studies relevant to our research. This paper provides three main contributions. First, we identify the existing machine learning algorithms for labeling and we present a taxonomy of these algorithms. Second, we identify the datasets that are used to evaluate the algorithms and we provide a mapping of the datasets based on the type of data and the application area. Third, we provide a process to support people in industry to optimally label their dataset. The results presented in this paper can be used by both researchers and practitioners aiming to improve the missing labels with the aid of machine algorithms or to select appropriate datasets to compare new state-of-the art algorithms in their respective application area.
23.	Fredriksson, Teodor, 1992, et al. (författare) Machine learning models for automatic labeling: A systematic literature review 2020 Ingår i: ICSOFT 2020 - Proceedings of the 15th International Conference on Software Technologies. - : SCITEPRESS - Science and Technology Publications. ; , s. 552-566 Konferensbidrag (refereegranskat)abstract Automatic labeling is a type of classification problem. Classification has been studied with the help of statistical methods for a long time. With the explosion of new better computer processing units (CPUs) and graphical processing units (GPUs) the interest in machine learning has grown exponentially and we can use both statistical learning algorithms as well as deep neural networks (DNNs) to solve the classification tasks. Classification is a supervised machine learning problem and there exists a large amount of methodology for performing such task. However, it is very rare in industrial applications that data is fully labeled which is why we need good methodology to obtain error-free labels. The purpose of this paper is to examine the current literature on how to perform labeling using ML, we will compare these models in terms of popularity and on what datatypes they are used on. We performed a systematic literature review of empirical studies for machine learning for labeling. We identified 43 primary studies relevant to our search. From this we were able to determine the most common machine learning models for labeling. Lack of unlabeled instances is a major problem for industry as supervised learning is the most widely used. Obtaining labels is costly in terms of labor and financial costs. Based on our findings in this review we present alternate ways for labeling data for use in supervised learning tasks.
24.	Hagström, Lovisa, 1995 (författare) A Picture is Worth a Thousand Words: Natural Language Processing in Context 2023 Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract Modern NLP models learn language from lexical co-occurrences. While this method has allowed for significant breakthroughs, it has also exposed potential limitations of modern NLP methods. For example, NLP models are prone to hallucinate, represent a biased world view and may learn spurious correlations to solve the data instead of the task at hand. This is to some extent the consequence of training the models exclusively on text. In text, concepts are only defined by the words that accompany them and the information in text is incomplete due to reporting bias. In this work, we investigate whether additional context in the form of multimodal information can be used to improve on the representations of modern NLP models. Specifically, we consider BERT-based vision-and-language models that receive additional context from images. We hypothesize that visual training primarily should improve on the visual commonsense knowledge, i.e. obvious knowledge about visual properties, of the models. To probe for this knowledge we develop the evaluation tasks Memory Colors and Visual Property Norms. Generally, we find that the vision-and-language models considered do not outperform unimodal model counterparts. In addition to this, we find that the models switch their answer depending on prompt when evaluated for the same type of knowledge. We conclude that more work is needed on understanding and developing vision-and-language models, and that extra focus should be put on how to successfully fuse image and language processing. We also reconsider the usefulness of measuring commonsense knowledge in models that cannot represent factual knowledge.
25.	Hagström, Lovisa, 1995, et al. (författare) What do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge 2022 Ingår i: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pp. 252–261, Dublin, Ireland. - : Association for Computational Linguistics. - 9781955917230 Konferensbidrag (refereegranskat)abstract There are limitations in learning language from text alone. Therefore, recent focus has been on developing multimodal models. However, few benchmarks exist that can measure what language models learn about language from multimodal training. We hypothesize that training on a visual modality should improve on the visual commonsense knowledge in language models. Therefore, we introduce two evaluation tasks for measuring visual commonsense knowledge in language models (code publicly available at: github.com/lovhag/measure-visual-commonsense-knowledge) and use them to evaluate different multimodal models and unimodal baselines. Primarily, we find that the visual commonsense knowledge is not significantly different between the multimodal models and unimodal baseline models trained on visual text data.
26.	Hamon, Thierry, et al. (författare) Combining Compositionality and Pagerank for the Identification of Semantic Relations between Biomedical Words 2012 Ingår i: BioNLP. - 9781937284206 - 1937284204 ; , s. 109-117 Konferensbidrag (refereegranskat)abstract The acquisition of semantic resources and relations is an important task for several applications, such as query expansion, information retrieval and extraction, machine translation. However, their validity should also be computed and indicated, especially for automatic systems and applications. We exploit the compositionality based methods for the acquisition of synonymy relations and of indicators of these synonyms. We then apply pagerank-derived algorithm to the obtained semantic graph in order to filter out the acquired synonyms. Evaluation performed with two independent experts indicates that the quality of synonyms is systematically improved by 10 to 15% after their filtering.
27.	Lange, Herbert, 1987, et al. (författare) Learning Domain-Specific Grammars from a Small Number of Examples 2021 Ingår i: Studies in Computational Intelligence. - Cham : Springer International Publishing. - 1860-9503 .- 1860-949X. - 9783030637873 ; 939, s. 105-138 Konferensbidrag (refereegranskat)abstract In this chapter we investigate the problem of grammar learning from a perspective that diverges from previous approaches. These prevailing approaches to learning grammars usually attempt to infer a grammar directly from example corpora without any additional information. This either requires a large training set or suffers from bad accuracy. We instead view learning grammars as a problem of grammar restriction or subgrammar extraction. We start from a large-scale grammar (called a resource grammar) and a small number of example sentences, and find a subgrammar that still covers all the examples. To accomplish this, we formulate the problem as a constraint satisfaction problem, and use a constraint solver to find the optimal grammar. We created experiments with English, Finnish, German, Swedish, and Spanish, which show that 10–20 examples are often sufficient to learn an interesting grammar for a specific application. We also present two extensions to this basic method: we include negative examples and allow rules to be merged. The resulting grammars can more precisely cover specific linguistic phenomena. Our method, together with the extensions, can be used to provide a grammar learning system for specific applications. This system is easy-to-use, human-centric, and can be used by non-syntacticians. Based on this grammar learning method, we can build applications for computer-assisted language learning and interlingual communication, which rely heavily on the knowledge of language and domain experts who often lack the competence to develop required grammars themselves.
28.	Norlund, Tobias, 1991 (författare) Improving Language Models Using Augmentation and Multi-Modality 2023 Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract Language models have become a core component in modern Natural Language Processing (NLP) as they constitute a powerful base that is easily adaptable to many language processing tasks. Part of the strength lies in their ability to embed associations representing general world knowledge. However, the associations formed by these models are brittle, even when scaled to huge sizes and using massive amounts of data. This, in combination with other problems such as lack of attributability and high costs, motivate us to investigate other methods to improve on these aspects. In this thesis, we investigate methods that augment language models with additional contextual information, for the purpose of simplifying the language modeling problem and increasing the formation of desirable associations. We also investigate whether multi-modal data can assist in forming such associations, that could otherwise be difficult to obtain from textual data only. In our experiments, we showcase augmentation to be effective toward these ends, in both a textual and multi-modal case. We also demonstrate that visual data can assist in forming knowledge-representing associations in a language model.
29.	Norlund, Tobias, 1991, et al. (författare) On the Generalization Ability of Retrieval-Enhanced Transformers 2023 Ingår i: Findings of the Association for Computational Linguistics: EACL 2023, pages 1485–1493, Dubrovnik, Croatia. - : Association for Computational Linguistics. ; , s. 1485-1493 Konferensbidrag (refereegranskat)abstract Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown impressive results: off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models that are an order of magnitude larger in size. It has been suggested that at least some of this performance gain is due to non-trivial generalization based on both model weights and retrieval. In this paper, we try to better understand the relative contributions of these two components. We find that the performance gains from retrieval to a very large extent originate from overlapping tokens between the database and the test data, suggesting less of non-trivial generalization than previously assumed. More generally, our results point to the challenges of evaluating the generalization of retrieval-augmented language models such as RETRO, as even limited token overlap may significantly decrease test-time loss. We release our code and model at https://github.com/TobiasNorlund/retro
30.	Shavalieva, Gulnara, 1987, et al. (författare) Knowledge mining from scientific literature for acute aquatic toxicity: classification for hybrid predictive modelling 2022 Ingår i: Computer Aided Chemical Engineering. - 1570-7946. ; 51, s. 1465-1470 Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract This work proposes a systematic method consisting of state-of-the-art text processing approaches and human-machine interaction for the extraction of useful sentences and data in tabular, graphical, and numerical form, containing information particularly relevant for hybrid modelling. It is applied to the domain of acute aquatic toxicity of chemicals, which is particularly relevant for the safety, health, and environmental hazard assessment of chemicals. Nearly 400 papers from 2000-2021 were identified and processed with the proposed method. The results indicate that the vast amount of knowledge can be efficiently processed in orders of magnitude faster than conventional methods without loss of detail and interpretation depth. The information is in a form that can be useful in hybrid modelling with respect to model and predictor selection, prioritization, and constraints, addressing data gaps, and validating and interpreting model performance.
31.	Snickars, Pelle (författare) 100 miljoner ord : Reflektioner kring forskningsarbete med storskaliga dataset som historisk empiri 2022 Ingår i: Historisk Tidskrift. - 0345-469X. ; 142:3, s. 320-352 Tidskriftsartikel (refereegranskat)abstract A hundred million words: Reflections on historical research with large-scale textual datasets as empirical evidenceThe research project Welfare State Analytics: Text Mining and Modelling Swedish Politics, Media & Culture, 1945–1989 uses probabilistic methods and text-mining models to study three massive textual datasets from Swedish politics, news media, and literary culture. By topic modelling and distant reading a dataset from some 3,100 Swedish Government Official Reports, findings have been made which previous historical scholarship has neglected – or rather, cannot detect because of the limitations of traditional, smallscale examinations of only a few such reports. This article presents some of the project’s findings, but concentrates on the practical issues of curating large-scale textual datasets, and thus the possibilities – and shortcomings – of digital history research practices.Large-scale textual datasets, often containing hundreds of millions of words, are a new type of empirical material that presents the historian with fresh challenges. The preparation of datasets is usually a resource-intensive task, where algorithmic machine learning is combined with the manual curation of data, a process that compiles the empirical material into datasets (in different versions).Plainly, historical empirical material must be compiled into datasets to enable large-scale analyses, and such work can be laborious, as it depends on extensive programming efforts; what may come as a surprise is how complicated the relationship between data and empirical material can be in a digital-historical context, and the fact that preparing datasets is usually an iterative procedure that fundamentally changes the historical sources. In this type of research, compiled empirical material will usually result in several datasets, depending not only on how effective the available software is to curate and correct errors but also the specific research questions – given that data can be modelled in many ways. The relationship between empirical material and curated datasets is therefore complex, and highly dependent on both software and research practices.
32.	Toll, Daniel, et al. (författare) The challenge of teaching students the value of programming best practices 2014 Ingår i: ITICSE 2014 - Proceedings of the 2014 Innovation and Technology in Computer Science Education Conference. - New York, New York, USA : Association for Computing Machinery (ACM). - 9781450328333 Konferensbidrag (refereegranskat)abstract We investigate the benefits of our programming assignments in correlation to what the students learn and show in their programming solutions. The assignments are supposed to teach the students to use best practices related to program comprehension, but do the programming assignments clearly show the benefits of best practices? We performed an experiment that showed no significant result which suggests that the assignments did not emphasise the value of best practices. As lecturers, we understand that constructing assignments that match the sought after outcome in students learning is a complex task. The experiment provided valuable insights that we will use to improve the assignments to better mirror best practices.
33.	Tomé Cortiñas, Carlos, 1990, et al. (författare) Simple Noninterference by Normalization 2019 Ingår i: Proceedings of the ACM Conference on Computer and Communications Security. - New York, NY, USA : ACM. - 1543-7221. ; , s. 61-72 Konferensbidrag (refereegranskat)abstract Information-flow control (IFC) languages ensure programs preserve the confidentiality of sensitive data. Noninterference, the desired security property of such languages, states that public outputs of programs must not depend on sensitive inputs. In this paper, we show that noninterference can be proved using normalization. Unlike arbitrary terms, normal forms of programs are well-principled and obey useful syntactic properties-hence enabling a simpler proof of noninterference. Since our proof is syntax-directed, it offers an appealing alternative to traditional semantic based techniques to prove noninterference. In particular, we prove noninterference for a static IFC calculus, based on Haskell's seclib library, using normalization. Our proof follows by straightforward induction on the structure of normal forms. We implement normalization using normalization by evaluation and prove that the generated normal forms preserve semantics. Our results have been verified in the Agda proof assistant.
34.	Wahde, Mattias, 1969 (författare) Models with verbally enunciated explanations: Towards safe, accountable, and trustworthy artificial intelligence 2024 Ingår i: International Conference on Agents and Artificial Intelligence. - 2184-433X .- 2184-3589. ; 3, s. 101-108 Konferensbidrag (refereegranskat)abstract In this position paper, we propose a new approach to artificial intelligence (AI), involving systems, abbreviated MOVEEs, that are capable of generating a verbally enunciated explanation of their actions, such that the explanation is also correct by construction. The possibility of obtaining a human-understandable, verbal explanation of any action or decision taken by an AI system is highly desirable, and is becoming increasingly important at this time when many AI systems operate as inscrutable black boxes. We describe the desirable properties of the proposed systems, contrasting them with existing AI approaches. We also discuss limitations and possible applications. While the discussion is mostly held in general terms, we also provide a specific example of a completed system, as well as a few examples of ongoing and future work.
35.	Wilhelmsson, Kenneth (författare) Automatic Question Generation from Swedish Documents as a Tool for Information Extraction 2011 Ingår i: Proceedings of the 18th Nordic Conference of Computational Linguistics NODALIDA 2011. ; , s. 323-326 Konferensbidrag (refereegranskat)abstract An implementation of automatic question generation (QG) from raw Swedish text is presented. QG is here chosen as an alternative to natural query systems where any query can be posed and no indication is given of whether the current text database includes the information sought for. The program builds on parsing with grammatical functions from which corresponding questions are generated and it incorporates the article database of Swedish Wikipedia. The pilot system is meant to work with a text shown in the GUI and auto-completes user input to help find available questions. The act of question generation is here described together with early test results regarding the current produced questions.
36.	Yu, Yinan, 1985, et al. (författare) climateBUG: A data-driven framework for analyzing bank reporting through a climate lens 2024 Ingår i: Expert Systems with Applications. - 0957-4174 .- 1873-6793. ; 239 Tidskriftsartikel (refereegranskat)abstract This paper applies computational linguistics learning methods to the banking industry and climate change fields. We introduce our data-driven framework, climateBUG, with the aim of detecting latent information about how banks discuss their activities related to climate change using natural language processing (NLP). This framework consists of an ingestion pipeline, a configurable database, and a set of API’s. In addition, climateBUG offers two standalone components, namely a unique annotated corpus of approximately 1.1M statements from EU banks’ annual and sustainability reporting and a deep learning model adapted to the semantics of the corpus. When benchmarking on classification performance, our model outperforms other models with similar scopes due to its stronger domain relevance. We also provide examples of how the framework can be applied from a user perspective.
37.	Bernardy, Jean-Philippe, 1978, et al. (författare) Efficient parallel and incremental parsing of practical context-free languages 2015 Ingår i: Journal of Functional Programming. - : Cambridge University Press (CUP). - 1469-7653 .- 0956-7968. ; 25, s. Article Number: UNSP e10- Tidskriftsartikel (refereegranskat)abstract We present a divide-and-conquer algorithm for parsing context-free languages efficiently. Our algorithm is an instance of Valiant's (1975; General context-free recognition in less than cubic time. J. Comput. Syst. Sci. 10(2), 308-314), who reduced the problem of parsing to matrix multiplications. We show that, while the conquer step of Valiant's is O(n(3)), it improves to O(log(2) n) under certain conditions satisfied by many useful inputs that occur in practice, and if one uses a sparse representation of matrices. The improvement happens because the multiplications involve an overwhelming majority of empty matrices. This result is relevant to modern computing: divide-and-conquer algorithms with a polylogarithmic conquer step can be parallelized relatively easily.
38.	Dannélls, Dana, 1976, et al. (författare) A Two-OCR Engine Method for Digitized Swedish Newspapers 2021 Ingår i: Selected Papers from the CLARIN Annual Conference 2020, Linköping Electronic Conference Proceedings 180. - Linköping : Linköping University Electronic Press. - 1650-3686 .- 1650-3740. - 9789179296094 Konferensbidrag (refereegranskat)abstract In this paper we present a two-OCR engine method that was developed at Kungliga biblioteket (KB), the National Library of Sweden, for improving the correctness of the OCR for mass digitization of Swedish newspapers. To evaluate the method a reference material spanning the years 1818–2018 was prepared and manually transcribed. A quantitative evaluation was then performed against the material. In this first evaluation we experimented with word lists for different time periods. The results show that even though there was no significant overall improvement of the OCR results, some combinations of word lists are successful for certain periods and should therefore be explored further.
39.	Dravins, Christina, et al. (författare) Exploring and enjoying non-speech sounds through a cochlear implant: the therapy of music 2010 Ingår i: 11th International Conference on Cochlear Implants and other Implantable Technologies. - Karolinska University Hospital : Karolinska University Hospital. ; , s. 356- Konferensbidrag (refereegranskat)abstract Cochlear implant technology was initially designed to promote reception ofspeech sounds; however, music enjoyment remains a challenge. Music is aninfluential ingredient in our well-being, playing an important role in ourcognitive, physical and social development. For many cochlear implantrecipients it is not feasible to communicate how sounds are perceived, andconsequently the benefits of music listening may be reduced. Non-speechsounds may also be important to persons with multiple functional deficitsthat relay on information additional to verbatim for participating incommunication. Deaf-born children with multiple functional deficitsconstitute a special vulnerable group as lack of reaction to sound oftenis discouraging to caregivers. Individually adapted tools and methods forsound awareness may promote exploration and appreciation of theinformation mediated by the implant.Two current works involving habilitation through sound production andmusic will be discussed. First, the results from a pilot study aiming atfinding musical toys that can be adapted to help children explore theirhearing with engaging sounds and expressive interfaces will be presented.The findings indicate that children with multiple functional deficits canbe more inclined to use the auditory channel for communication and playthan the caregivers would anticipate.Second, the results of a recent questionnaire study, which compared themusic exposure and appreciation of preschool cochlear implant recipientswith their normally hearing peers will be presented. The data from thisstudy indicate that preschool children with cochlear implants spendroughly the same amount of time interacting with musical instruments athome and watching television programmes and DVDs which include music.However, the data indicate that these children receive less exposure torecorded music without visual stimuli and show less sophisticatedresponses to music. The provision and supported use of habilitationmaterials which encourage interaction with music might therefore bebeneficial.
40.	Hammarstedt, Martin, et al. (författare) Sparv 5 Developer’s Guide 2022 Rapport (övrigt vetenskapligt/konstnärligt)abstract The Sparv Pipeline developed by Språkbanken Text is a text analysis tool run from the command line. This Developer’s Guide describes its general structure and key concepts and serves as an API documentation. Most importantly, it describes how to write plugins for Sparv 5 so that you can add your own functions to the toolkit.
41.	Hansen, Kjetil Falkenberg, 1972-, et al. (författare) Sonification of distance between stations in train journeys 2012 Ingår i: TMH-QPSR special issue: Proceedings of SMC Sweden 2012 Sound and Music Computing, Understanding and Practicing in Sweden. - Stockholm : Department of Speech, Music and Hearing, Royal Institute of Technology. - 1104-5787. ; 52:1, s. 13-14, s. 13-14 Tidskriftsartikel (refereegranskat)
42.	Hansen, Kjetil Falkenberg, 1972-, et al. (författare) Using modern smartphones to create interactive listening experiences for hearing impaired 2012 Ingår i: TMH-QPSR special issue: Proceedings of SMC Sweden 2012 Sound and Music Computing, Understanding and Practicing in Sweden. - Stockholm : TMH KTH. - 1104-5787. ; 52:1, s. 42-, s. 42- Tidskriftsartikel (refereegranskat)
43.	Hasibi, Faegheh (författare) An Adaptation Technique for GF-Based Dialogue Systems 2012 Ingår i: Controlled Natural Language, Lecture Notes in Computer Science. - 9783642326110 ; 7427, s. 95-109 Konferensbidrag (refereegranskat)abstract This paper introduces a technique for adapting GF (Grammatical Framework)-based dialogue systems. This technique can be used to adapt dialogue systems in two aspects: user adaptation and self-adaptation. By user adaptation, users can customize the system to their own needs and define alternatives for a series of information to use in later utterances. By self-adaptation, the system can update GF grammar to keep the system adequate when new situations occur. This technique is demonstrated by a multi-lingual transport query system, which allows users to find up-to-date travel plans. Adapting GF-based dialogue systems improves the functionality of speech recognizers by defining alternatives for specific phrases and also keeps the dialogue system always updated.
44.	Johansson, Simon, 1994, et al. (författare) Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction 2022 Ingår i: Molecular Informatics. - : Wiley. - 1868-1743 .- 1868-1751. ; 41:12 Tidskriftsartikel (refereegranskat)abstract Computer aided synthesis planning, suggesting synthetic routes for molecules of interest, is a rapidly growing field. The machine learning methods used are often dependent on access to large datasets for training, but finite experimental budgets limit how much data can be obtained from experiments. This suggests the use of schemes for data collection such as active learning, which identifies the data points of highest impact for model accuracy, and which has been used in recent studies with success. However, little has been done to explore the robustness of the methods predicting reaction yield when used together with active learning to reduce the amount of experimental data needed for training. This study aims to investigate the influence of machine learning algorithms and the number of initial data points on reaction yield prediction for two public high-throughput experimentation datasets. Our results show that active learning based on output margin reached a pre-defined AUROC faster than random sampling on both datasets. Analysis of feature importance of the trained machine learning models suggests active learning had a larger influence on the model accuracy when only a few features were important for the model prediction.
45.	Kavathatzopoulos, Iordanis (författare) New technologies in the education of native language 2004 Ingår i: Greek language education in Scandinavia. ; , s. 73-76 Konferensbidrag (refereegranskat)abstract Education in mother tongue as well as any education, demands the use of adequate methods and tools to be effective. New technology offers many possibilities for this purpose. In the present paper different IT solutions are discussed and their contribution to the goal of learning the mother tongue are examined. Necessary conditions for successful learning are supposed to be the careful choice and the continuous adaptation of used IT tools to the psychological learning process of the child.
46.	Kokkinakis, Dimitrios, 1965, et al. (författare) Query Logs as a Corpus. 2013 Ingår i: Corpus Linguistics 2013 : abstract book. Lancaster: UCREL / edited by Andrew Hardie and Robbie Love. Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract This paper provides a detailed description of a large Swedish health-related query log corpus and explores means to derive useful statistics, their distributions and analytics from its content across several dimensions. Information acquisition from query logs can be useful for several purposes and potential types of users, such as terminologists, infodemiologists / epidemiologists, medical data and web analysts, specialists in NLP technologies such as information retrieval and text mining but also public officials in health and safety organizations.
47.	Lambers, L., et al. (författare) Granularity of conflicts and dependencies in graph transformation systems: A two-dimensional approach 2019 Ingår i: Journal of Logical and Algebraic Methods in Programming. - : Elsevier BV. - 2352-2208 .- 2352-2216. ; 103, s. 105-129 Tidskriftsartikel (refereegranskat)abstract Conflict and dependency analysis (CDA) is a static analysis for the detection of conflicting and dependent rule applications in a graph transformation system. The state-of-the-art CDA technique, critical pair analysis, provides all potential conflicts and dependencies in minimal context as critical pairs, for each pair of rules. Yet, critical pairs can be hard to understand; users are mainly interested in core information about conflicts and dependencies occurring in various combinations. In this paper, we present an approach to conflicts and dependencies in graph transformation systems based on two dimensions of granularity. The first dimension refers to the overlap considered between the rules of a given rule pair; the second one refers to the represented amount of context information about transformations in which the conflicts occur. We introduce a variety of new conflict notions, in particular, conflict atoms, conflict reasons, and minimal conflict reasons, relate them to the existing conflict notions of critical pairs and initial conflicts, and position all of these notions within our granularity approach. Finally, we introduce dual concepts for dependency analysis. As we discuss in a running example, our approach paves the way for an improved CDA technique. (C) 2018 Elsevier Inc. All rights reserved.
48.	Laukka, Petri, et al. (författare) Expression of affect in spontaneous speech : Acoustic correlates and automatic detection of irritation and resignation 2011 Ingår i: Computer speech & language (Print). - : Elsevier. - 0885-2308 .- 1095-8363. ; 25:1, s. 84-104 Tidskriftsartikel (refereegranskat)abstract The majority of previous studies on vocal expression have been conducted on posed expressions. In contrast, we utilized a large corpus of authentic affective speech recorded from real-life voice controlled telephone services. Listeners rated a selection of 200 utterances from this corpus with regard to level of perceived irritation, resignation, neutrality, and emotion intensity. The selected utterances came from 64 different speakers who each provided both neutral and affective stimuli. All utterances were further automatically analyzed regarding a comprehensive set of acoustic measures related to F0, intensity, formants, voice source, and temporal characteristics of speech. Results first showed that several significant acoustic differences were found between utterances classified as neutral and utterances classified as irritated or resigned using a within-persons design. Second, listeners’ ratings on each scale were associated with several acoustic measures. In general the acoustic correlates of irritation, resignation, and emotion intensity were similar to previous findings obtained with posed expressions, though the effect sizes were smaller for the authentic expressions. Third, automatic classification (using LDA classifiers both with and without speaker adaptation) of irritation, resignation, and neutral performed at a level comparable to human performance, though human listeners and machines did not necessarily classify individual utterances similarly. Fourth, clearly perceived exemplars of irritation and resignation were rare in our corpus. These findings were discussed in relation to future research.
49.	Li, Zheng, et al. (författare) Music Puzzle: An Application for Hearing Training on Android Smart Devices 2012 Ingår i: TMH-QPSR special issue: Proceedings of SMC Sweden 2012 Sound and Music Computing, Understanding and Practicing in Sweden. - Stockholm. - 1104-5787. ; 52:1, s. 44-45, s. 44-45 Tidskriftsartikel (refereegranskat)abstract The Music Puzzle is part of an ongoing project called Ljudparken/The Soundpark – Using modern smartphones to create interactive listening experiences for hearing impaired. The aim is to create interactive listening experiences for Deaf or Hard-of-Hearing persons (DHH). The interaction is carried out through using new sensor-based audio interfaces.
50.	Medved, Dennis (författare) Applications of Machine Learning on Natural Language Processing and Biomedical Data 2017 Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract Machine learning is ubiquitous in today’s society, with promising applicationsin the field of natural language processing (NLP), so that computers can handlehuman language better, and within the medical community, with the promiseof better treatments. Machine learning can be seen as a subfield of artificialintelligence (AI), where AI is used to describe a machine that mimics cognitivefunctions that humans associate with other human minds, such as learning orproblem solving.In this thesis we explore how machine learning can be used to improve classification of picture, by using associated text. We then shift our focus to biomedical data, specifically heart transplantation patients. We show how the data can be represented as a graph database using the resource description framework (RDF).After that we use the data with logistic regression and the Spark framework, toperform feature search to predict the survival probability of the patients. In thetwo last articles we use artificial neural networks (ANN) first to predict patientsurvival, and compare it with a logistic regression approach, and last to predict the outcome of patients awaiting heart transplantation.We plan to do simulation of different allocation policies, for donor hearts, usingthese kind of ANNs, to be able to asses their impact on predicted earned survivaltime.

Skapa referenser, mejla, bekava och länka

Länka till träfflistan

Träfflista för sökning "hsv:(NATURVETENSKAP) hsv:(Data och informationsvetenskap) hsv:(Språkteknologi) "

Avgränsa träffmängd

År