Design and Implementation of a Short Answer Scoring System to give feedback about textual similarity
keywords:
Deep Learning, Semantic Similarity, Short Answer Scoring
Description:
Feedback on Short Answer Scoring.
Objectives:
The objective of this thesis is to research on the interpretation of textual similarities between sentences in order to give feedback when answering questions. The identification of key-snippets is fundamental to identify which knowledge is relevant when giving explanations about the similarities and diferences between users' answers and reference answers. The identification of the key-snippets will allow the system to focus on the relevant information for the feedback.
Task:
- Building an iSTS system that generates verbalizations of similarities between texts.
- Micro Question Answering: Identification of answers on specific texts
- Natural Language Generation: Reformulation of humans' answers
- Evaluation techniques for the previous tasks.
- Applications on Digital humanities and Educational Technology (e.g. content assessment of reading comprehension, …)
- Micro Question Answering: Identification of answers on specific texts
- Natural Language Generation: Reformulation of humans' answers
- Evaluation techniques for the previous tasks.
- Applications on Digital humanities and Educational Technology (e.g. content assessment of reading comprehension, …)
References:
[1] Michael Hahn and Detmar Meurers. (2012). Evaluating the meaning of answers to reading comprehension questions: a semantics-based approach. In Proceedings of the Seventh Workshop on Building Educational Applications Using NLP. Association for Computational Linguistics, Stroudsburg, PA, USA, 326-336.
[2] I. Lopez-Gazpio and M. Maritxalar and A. Gonzalez-Agirre and G. Rigau and L. Uria and E. Agirre (2017) Interpretable Semantic Textual Similarity: Finding and explaining differences between sentences. Knowledge-Based Systems (KNOSYS). Volume 119, Pages 186–199. ISSN: 0950-7051. Editorial: Elsevier.
[3] Kai Sheng Tai, Richard Socher, and Christopher D. Manning. (2015). Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 1556-1566, Beijing, China, July. Association for Computational Linguistics.
[4] Ziai, R., & Meurers, D. (2014). Focus Annotation in Reading Comprehension Data. In LAW@ COLING (pp. 159-168).
[2] I. Lopez-Gazpio and M. Maritxalar and A. Gonzalez-Agirre and G. Rigau and L. Uria and E. Agirre (2017) Interpretable Semantic Textual Similarity: Finding and explaining differences between sentences. Knowledge-Based Systems (KNOSYS). Volume 119, Pages 186–199. ISSN: 0950-7051. Editorial: Elsevier.
[3] Kai Sheng Tai, Richard Socher, and Christopher D. Manning. (2015). Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 1556-1566, Beijing, China, July. Association for Computational Linguistics.
[4] Ziai, R., & Meurers, D. (2014). Focus Annotation in Reading Comprehension Data. In LAW@ COLING (pp. 159-168).
Team:
Eneko Agirre, Iñigo Lopez, Montse Maritxalar
Profile:
Computer scientist
File:
contact:
montse.maritxalar[abildua|at]ehu.eus
Date:
2017