| 1. |
|
|
| 2. |
- Arpteg, Anders, 1974-
(författare)
-
Adaptive Semi-structured Information Extraction
- 2003
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The number of domains and tasks where information extraction tools can be used needs to be increased. One way to reach this goal is to construct user-driven information extraction systems where novice users are able to adapt them to new domains and tasks. To accomplish this goal, the systems need to become more intelligent and able to learn to extract information without need of expert skills or time-consuming work from the user.The type of information extraction system that is in focus for this thesis is semistructural information extraction. The term semi-structural refers to documents that not only contain natural language text but also additional structural information. The typical application is information extraction from World Wide Web hypertext documents. By making effective use of not only the link structure but also the structural information within each such document, user-driven extraction systems with high performance can be built.The extraction process contains several steps where different types of techniques are used. Examples of such types of techniques are those that take advantage of structural, pure syntactic, linguistic, and semantic information. The first step that is in focus for this thesis is the navigation step that takes advantage of the structural information. It is only one part of a complete extraction system, but it is an important part. The use of reinforcement learning algorithms for the navigation step can make the adaptation of the system to new tasks and domains more user-driven. The advantage of using reinforcement learning techniques is that the extraction agent can efficiently learn from its own experience without need for intensive user interactions.An agent-oriented system was designed to evaluate the approach suggested in this thesis. Initial experiments showed that the training of the navigation step and the approach of the system was promising. However, additional components need to be included in the system before it becomes a fully-fledged user-driven system.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
| 11. |
- Arpteg, Anders, 1974-
(författare)
-
Intelligent semi-structured information extraction : a user-driven approach to information extraction
- 2005
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The number of domains and tasks where information extraction tools can be used needs to be increased. One way to reach this goal is to design user-driven information extraction systems where non-expert users are able to adapt them to new domains and tasks. It is difficult to design general extraction systems that do not require expert skills or a large amount of work from the user. Therefore, it is difficult to increase the number of domains and tasks. A possible alternative is to design user-driven systems, which solve that problem by letting a large number of non-expert users adapt the systems themselves. To accomplish this goal, the systems need to become more intelligent and able to learn to extract with as little given information as possible.The type of information extraction system that is in focus for this thesis is semi-structured information extraction. The term semi-structured refers to documents that not only contain natural language text but also additional structural information. The typical application is information extraction from World Wide Web hypertext documents. By making effective use of not only the link structure but also the structural information within each such document, user-driven extraction systems with high performance can be built.There are two different approaches presented in this thesis to solve the user-driven extraction problem. The first takes a machine learning approach and tries to solve the problem using a modified $Q(\lambda)$ reinforcement learning algorithm. A problem with the first approach was that it was difficult to handle extraction from the hidden Web. Since the hidden Web is about 500 times larger than the visible Web, it would be very useful to be able to extract information from that part of the Web as well. The second approach is called the hidden observation approach and tries to also solve the problem of extracting from the hidden Web. The goal is to have a user-driven information extraction system that is also able to handle the hidden Web. The second approach uses a large part of the system developed for the first approach, but the additional information that is silently obtained from the user presents other problems and possibilities.An agent-oriented system was designed to evaluate the approaches presented in this thesis. A set of experiments was conducted and the results indicate that a user-driven information extraction system is possible and no longer just a concept. However, additional work and research is necessary before a fully-fledged user-driven system can be designed.
|
|
| 12. |
|
|
| 13. |
|
|
| 14. |
- Arpteg, Anders
(författare)
-
Multi-Page List Extraction
- 2005
-
Ingår i: Proceedings of the International Conference on Integration of Knowledge Intensive Multi-Agent Systems.
-
Konferensbidrag (refereegranskat)
|
|
| 15. |
|
|
| 16. |
|
|
| 17. |
- Arpteg, Anders
(författare)
-
Riskkapital till forskare
- 2007
-
Ingår i: Östra Småland.
-
Tidskriftsartikel (populärvet., debatt m.m.)
|
|
| 18. |
- Arpteg, Anders
(författare)
-
Semi-Structured Complex List Extraction
- 2004
-
Ingår i: 2nd International Conference on Web Intelligence, workshop on Web-based Support Systems, Beijing, China.
-
Konferensbidrag (refereegranskat)
|
|
| 19. |
|
|
| 20. |
- Erliksson, Karl Fredrik, et al.
(författare)
-
Cross-Domain Transfer of Generative Explanations Using Text-to-Text Models
- 2021
-
Ingår i: Lecture Notes in Computer Science. - Cham : Springer Nature. ; , s. 76-89
-
Konferensbidrag (refereegranskat)abstract
- Deep learning models based on the Transformers architecture have achieved impressive state-of-the-art results and even surpassed human-level performance across various natural language processing tasks. However, these models remain opaque and hard to explain due to their vast complexity and size. This limits adoption in highly-regulated domains like medicine and finance, and often there is a lack of trust from non-expert end-users. In this paper, we show that by teaching a model to generate explanations alongside its predictions on a large annotated dataset, we can transfer this capability to a low-resource task in another domain. Our proposed three-step training procedure improves explanation quality by up to 7% and avoids sacrificing classification performance on the downstream task, while at the same time reducing the need for human annotations.
|
|
| 21. |
- Munappy, Aiswarya Raj, 1990, et al.
(författare)
-
Data Management Challenges for Deep Learning
- 2019
-
Ingår i: Proceedings - 45th Euromicro Conference on Software Engineering and Advanced Applications, SEAA 2019. - : IEEE. ; , s. 140-147
-
Konferensbidrag (refereegranskat)abstract
- © 2019 IEEE. Deep learning is one of the most exciting and fast-growing techniques in Artificial Intelligence. The unique capacity of deep learning models to automatically learn patterns from the data differentiates it from other machine learning techniques. Deep learning is responsible for a significant number of recent breakthroughs in AI. However, deep learning models are highly dependent on the underlying data. So, consistency, accuracy, and completeness of data is essential for a deep learning model. Thus, data management principles and practices need to be adopted throughout the development process of deep learning models. The objective of this study is to identify and categorise data management challenges faced by practitioners in different stages of end-to-end development. In this paper, a case study approach is employed to explore the data management issues faced by practitioners across various domains when they use real-world data for training and deploying deep learning models. Our case study is intended to provide valuable insights to the deep learning community as well as for data scientists to guide discussion and future research in applied deep learning with real-world data.
|
|
| 22. |
- Munappy, Aiswarya Raj, 1990, et al.
(författare)
-
Data management for production quality deep learning models: Challenges and solutions
- 2022
-
Ingår i: Journal of Systems and Software. - : Elsevier BV. - 0164-1212 .- 1873-1228. ; 191
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning (DL) based software systems are difficult to develop and maintain in industrial settings due to several challenges. Data management is one of the most prominent challenges which complicates DL in industrial deployments. DL models are data-hungry and require high-quality data. Therefore, the volume, variety, velocity, and quality of data cannot be compromised. This study aims to explore the data management challenges encountered by practitioners developing systems with DL components, identify the potential solutions from the literature and validate the solutions through a multiple case study. We identified 20 data management challenges experienced by DL practitioners through a multiple interpretive case study. Further, we identified 48 articles through a systematic literature review that discuss the solutions for the data management challenges. With the second round of multiple case study, we show that many of these solutions have limitations and are not used in practice due to a combination of four factors: high cost, lack of skill-set and infrastructure, inability to solve the problem completely, and incompatibility with certain DL use cases. Thus, data management for data-intensive DL models in production is complicated. Although the DL technology has achieved very promising results, there is still a significant need for further research in the field of data management to build high-quality datasets and streams that can be used for building production-ready DL systems. Furthermore, we have classified the data management challenges into four categories based on the availability of the solutions.(c) 2022 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
|
|
| 23. |
|
|
