TU Darmstadt / ULB / TUbiblio

Representation Learning for Answer Selection with LSTM-Based Importance Weighting

Rücklé, Andreas and Gurevych, Iryna (2017):
Representation Learning for Answer Selection with LSTM-Based Importance Weighting.
In: Proceedings of the 12th International Conference on Computational Semantics (IWCS 2017), Association for Computational Linguistics, Montpellier, France, Volume 2: Short papers, [Online-Edition: http://aclweb.org/anthology/W17-6935],
[Conference or Workshop Item]

Abstract

We present an approach to non-factoid answer selection with a separate component based on BiLSTM to determine the importance of segments in the input. In contrast to other recently proposed attention-based models within the same area, we determine the importance while assuming the independence of questions and candidate answers. Experimental results show the effectiveness of our approach, which outperforms several state-of-the-art attention-based models on the recent non-factoid answer selection datasets InsuranceQA v1 and v2. We show that it is possible to perform effective importance weighting for answer selection without relying on the relatedness of questions and answers. The source code of our experiments is publicly available.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Rücklé, Andreas and Gurevych, Iryna
Title: Representation Learning for Answer Selection with LSTM-Based Importance Weighting
Language: English
Abstract:

We present an approach to non-factoid answer selection with a separate component based on BiLSTM to determine the importance of segments in the input. In contrast to other recently proposed attention-based models within the same area, we determine the importance while assuming the independence of questions and candidate answers. Experimental results show the effectiveness of our approach, which outperforms several state-of-the-art attention-based models on the recent non-factoid answer selection datasets InsuranceQA v1 and v2. We show that it is possible to perform effective importance weighting for answer selection without relying on the relatedness of questions and answers. The source code of our experiments is publicly available.

Title of Book: Proceedings of the 12th International Conference on Computational Semantics (IWCS 2017)
Volume: Volume 2: Short papers
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_p_QAEduInf;UKP_reviewed;reviewed
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Montpellier, France
Date Deposited: 14 Jul 2017 21:30
Official URL: http://aclweb.org/anthology/W17-6935
Identification Number: TUD-CS-2017-0184
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item