| 1. |
- Jorge, Emilio, 1992, et al.
(författare)
-
Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence.
- 2016
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Learning your first language is an incredible feat and not easily duplicated. Doing this using nothing but a few pictureless books, a corpus, would likely be impossible even for humans. As an alternative we propose to use situated interactions between agents as a driving force for communication, and the framework of Deep RecurrentQ-Networks (DRQN) for learning a common language grounded in the provided environment. We task the agents with interactive image search in the form of the game Guess Who?. The images from the game provide a non trivial environment for the agents to discuss and a natural grounding for the concepts they decide to encode in their communication. Our experiments show that it is possible to learn this task using DRQN and even more importantly that the words the agents use correspond to physical attributes present in the images that make up the agents environment.
|
|
| 2. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
A reinforcement-learning approach to efficient communication
- 2020
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 15:7
-
Tidskriftsartikel (refereegranskat)abstract
- We present a multi-agent computational approach to partitioning semantic spaces using reinforcement-learning (RL). Two agents communicate using a finite linguistic vocabulary in order to convey a concept. This is tested in the color domain, and a natural reinforcement learning mechanism is shown to converge to a scheme that achieves a near-optimal trade-off of simplicity versus communication efficiency. Results are presented both on the communication efficiency as well as on analyses of the resulting partitions of the color space. The effect of varying environmental factors such as noise is also studied. These results suggest that RL offers a powerful and flexible computational framework that can contribute to the development of communication schemes for color names that are near-optimal in an information-theoretic sense and may shape color-naming systems across languages. Our approach is not specific to color and can be used to explore cross-language variation in other semantic domains.
|
|
| 3. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
DeepColor: Reinforcement Learning optimizes information efficiency and well-formedness in color name partitioning
- 2018
-
Ingår i: CogSci 2018, 40th annual Cognitive Science Society meeting, Madison Wisconsin USA, July 25-28 2018. - Oakbrook Terrace, IL, USA : Cognitive Science Society. - 9780991196784
-
Konferensbidrag (refereegranskat)abstract
- As observed in the World Color Survey (WCS), some universal properties can be identified in color naming schemes over a large number of languages. For example, Regier, Kay, and Khetrapal (2007) and Regier, Kemp, and Kay (2015); Gibson et al. (2017) recently explained these universal patterns in terms of near optimal color partitions and information theoretic measures of efficiency of communication. Here, we introduce a computational learning framework with multi-agent systems trained by reinforcement learning to investigate these universal properties. We compare the results with Regier et al. (2007, 2015) and show that our model achieves excellent quantitative agreement. This work introduces a multi-agent reinforcement learning framework as a powerful and versatile tool to investigate such semantic universals in many domains and contribute significantly to central questions in cognitive science.
|
|
| 4. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
Extractive Summarization using Continuous Vector Space Models
- 2014
-
Ingår i: Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) EACL, April 26-30, 2014 Gothenburg, Sweden. - 9781937284947 ; , s. 31-39
-
Konferensbidrag (refereegranskat)abstract
- Automatic summarization can help users extract the most important pieces of information from the vast amount of text digitized into electronic form everyday. Central to automatic summarization is the notion of similarity between sentences in text. In this paper we propose the use of continuous vector representations for semantically aware representations of sentences as a basis for measuring similarity. We evaluate different compositionsfor sentence representation on a standard dataset using the ROUGE evaluation measures. Our experiments show that the evaluated methods improve the performance of a state-of-the-art summarization framework and strongly indicate the benefits of continuous word vector representations for automatic summarization.
|
|
| 5. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
Neural context embeddings for automatic discovery of word senses
- 2015
-
Ingår i: Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing. Denver, United States. - 9781941643464 ; , s. 25-32
-
Konferensbidrag (refereegranskat)abstract
- Word sense induction (WSI) is the problem of automatically building an inventory of senses for a set of target words using only a text corpus. We introduce a new method for embedding word instances and their context, for use in WSI. The method, Instance-context embedding (ICE), leverages neural word embeddings, and the correlation statistics they capture, to compute high quality embeddings of word contexts. In WSI, these context embeddings are clustered to find the word senses present in the text. ICE is based on a novel method for combining word embeddings using continuous Skip-gram, based on both se- mantic and a temporal aspects of context words. ICE is evaluated both in a new system, and in an extension to a previous system for WSI. In both cases, we surpass previous state-of-the-art, on the WSI task of SemEval-2013, which highlights the generality of ICE. Our proposed system achieves a 33% relative improvement.
|
|
| 6. |
- Kågebäck, Mikael, 1981
(författare)
-
Word Representations for Emergent Communication and Natural Language Processing
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The task of listing all semantic properties of a single word might seem manageable at first but as you unravel all the context dependent subtle variations in meaning that a word can encompass, you soon realize that precise mathematical definition of a word’s semantics is extremely difficult. In analogy, humans have no problem identifying their favorite pet in an image but the task of precisely defining how, is still beyond our capabilities. A solution that has proved effective in the visual domain is to solve the problem by learning abstract representations using machine learning. Inspired by the success of learned representations in computer vision, the line of work presented in this thesis will explore learned word representations in three different contexts. Starting in the domain of artificial languages, three computational frameworks for emergent communication between collaborating agents are developed in an attempt to study word representations that exhibit grounding of concepts. The first two are designed to emulate the natural development of discrete color words using deep reinforcement learning, and used to simulate the emergence of color terms that partition the continuous color spectra of visual light. The properties of the emerged color communication schema is compared to human languages to ensure its validity as a cognitive model, and subsequently the frameworks are utilized to explore central questions in cognitive science about universals in language within the semantic domain of color. Moving beyond the color domain, a third framework is developed for the less controlled environment of human faces and multi-step communication. Subsequently, as for the color domain we carefully analyze the semantic properties of the words emerged between the agents but in this case focusing on the grounding. Turning the attention to the empirical usefulness, different types of learned word representations are evaluated in the context of automatic document summarisation, word sense disambiguation, and word sense induction with results that show great potential for learned word representations in natural language processing by reaching state-of-the-art performance in all applications and outperforming previous methods in two out of three applications. Finally, although learned word representations seem to improve the performance of real world systems, they do also lack in interpretability when compared to classical hand-engineered representations. Acknowledging this, an effort is made towards construct- ing learned representations that regain some of that interpretability by designing and evaluating disentangled representations, which could be used to represent words in a more interpretable way in the future.
|
|
| 7. |
- Kågebäck, Mikael, 1981, et al.
(författare)
-
Word Sense Disambiguation using a Bidirectional LSTM
- 2016
-
Ingår i: 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V) at the 26th International Conference on Computational Linguistics (COLING 2016).
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present a clean, yet effective, model for word sense disambiguation. Our approach leverage a bidirectional long short-term memory network which is shared between all words. This enables the model to share statistical strength and to scale well with vocabularysize. The model is trained end-to-end, directly from the raw text to sense labels, and makes effective use of word order. We evaluate our approach on two standard datasets, using identical hyperparameter settings, which are in turn tuned on a third set of held out data. We employ no external resources (e.g. knowledge graphs, part-of-speech tagging, etc), language specific features, or hand crafted rules, but still achieve statistically equivalent results to the best state-of-the-art systems, that employ no such limitations.
|
|
| 8. |
- Kågebäck, Mikael, 1981
(författare)
-
Word Sense Embedded in Geometric Spaces - From Induction to Applications using Machine Learning
- 2016
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Words are not detached individuals but part of a beautiful interconnected web of related concepts, and to capture the full complexity of this web they need to be represented in a way that encapsulates all the semantic and syntactic facets of the language. Further, to enable computational processing they need to be expressed in a consistent manner so that similar properties are encoded in a similar way. In this thesis dense real valued vector representations, i.e. word embeddings, are extended and studied for their applicability to natural language processing (NLP). Word embeddings of two distinct flavors are presented as part of this thesis, sense aware word representations where different word senses are represented as distinct objects, and grounded word representations that are learned using multi-agent deep reinforcement learning to explicitly express properties of the physical world while the agents learn to play Guess Who?. The empirical usefulness of word embeddings are evaluated by employing them in a series of NLP related applications, i.e. word sense induction, word sense disambiguation, and automatic document summarisation. The results show great potential for word embeddings by outperforming previous state-of-the-art methods in two out of three applications, and achieving a statistically equivalent result in the third application but using a much simpler model than previous work.
|
|
| 9. |
- Mogren, Olof, 1980, et al.
(författare)
-
Extractive summarization by aggregating multiple similarities
- 2015
-
Ingår i: International Conference Recent Advances in Natural Language Processing, RANLP. - 1313-8502. ; 2015, s. 451-457
-
Konferensbidrag (refereegranskat)abstract
- News reports, social media streams, blogs, digitized archives and books are part of a plethora of reading sources that people face every day. This raises the question of how to best generate automatic summaries. Many existing methods for extracting summaries rely on comparing the similarity of two sentences in some way. We present new ways of measuring this similarity, based on sentiment analysis and continuous vector space representations, and show that combining these together with similarity measures from existing methods, helps to create better summaries. The finding is demonstrated with MULTSUM, a novel summarization method that uses ideas from kernel methods to combine sentence similarity measures. Submodular optimization is then used to produce summaries that take several different similarity measures into account. Our method improves over the state-of-the-art on standard benchmark datasets; it is also fast and scale to large document collections, and the results are statistically significant.
|
|
| 10. |
- Tahmasebi, Nina, 1982, et al.
(författare)
-
Visions and open challenges for a knowledge-based culturomics
- 2015
-
Ingår i: International Journal on Digital Libraries. - : Springer Science and Business Media LLC. - 1432-5012 .- 1432-1300. ; 15:2-4, s. 169-187
-
Tidskriftsartikel (refereegranskat)abstract
- The concept of culturomics was born out of the availability of massive amounts of textual data and the interest to make sense of cultural and language phenomena over time. Thus far however, culturomics has only made use of, and shown the great potential of, statistical methods. In this paper, we present a vision for a knowledge-based culturomics that complements traditional culturomics. We discuss the possibilities and challenges of combining knowledge-based methods with statistical methods and address major challenges that arise due to the nature of the data; diversity of sources, changes in language over time as well as temporal dynamics of information in general. We address all layers needed for knowledge-based culturomics, from natural language processing and relations to summaries and opinions.
|
|
