Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts
Jong-Hoon Oh, Kazuma Kadowaki, Julien Kloetzer, Ryu Iida, Kentaro Torisawa
Abstract
In this paper, we propose a method for why-question answering (why-QA) that uses an adversarial learning framework. Existing why-QA methods retrieve “answer passages” that usually consist of several sentences. These multi-sentence passages contain not only the reason sought by a why-question and its connection to the why-question, but also redundant and/or unrelated parts. We use our proposed “Adversarial networks for Generating compact-answer Representation” (AGR) to generate from a passage a vector representation of the non-redundant reason sought by a why-question and exploit the representation for judging whether the passage actually answers the why-question. Through a series of experiments using Japanese why-QA datasets, we show that these representations improve the performance of our why-QA neural model as well as that of a BERT-based why-QA model. We show that they also improve a state-of-the-art distantly supervised open-domain QA (DS-QA) method on publicly available English datasets, even though the target task is not a why-QA.- Anthology ID:
- P19-1414
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4227–4237
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/P19-1414/
- DOI:
- 10.18653/v1/P19-1414
- Cite (ACL):
- Jong-Hoon Oh, Kazuma Kadowaki, Julien Kloetzer, Ryu Iida, and Kentaro Torisawa. 2019. Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4227–4237, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts (Oh et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/P19-1414.pdf
- Data
- QUASAR, QUASAR-T, SQuAD, SearchQA, TriviaQA