Multi-style Generative Reading Comprehension

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2273–2284 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 2273 Multi-Style Generative Reading Comprehension Kyosuke Nishida1, Itsumi Saito1, Kosuke Nishida1, Kazutoshi Shinoda2∗, Atsushi Otsuka1, Hisako Asano1, Junji Tomita1 1NTT Media Intelligence Laboratory, NTT Corporation 2The University of Tokyo kyosuke.nishida@acm.org Abstract This study tackles generative reading compre- hension (RC), which consists of answering questions based on textual evidence and nat- ural language generation (NLG). We propose a multi-style abstractive summarization model for question answering, called Masque. The proposed model has two key characteristics. First, unlike most studies on RC that have fo- cused on extracting an answer span from the provided passages, our model instead focuses on generating a summary from the question and multiple passages. This serves to cover various answer styles required for real-world applications. Second, whereas previous stud- ies built a specific model for each answer style because of the difficulty of acquiring one gen- eral model, our approach learns multi-style an- swers within a model to improve the NLG ca- pability for all styles involved. This also en- ables our model to give an answer in the tar- get style. Experiments show that our model achieves state-of-the-art performance on the Q&A task and the Q&A + NLG task of MS MARCO 2.1 and the summary task of Nar- rativeQA. We observe that the transfer of the style-independent NLG capability to the target style is the key to its success. 1 Introduction Question answering has been a long-standing re- search problem. Recently, reading comprehension (RC), a challenge to answer a question given tex- tual evidence provided in a document set, has re- ceived much attention. Current mainstream stud- ies have treated RC as a process of extracting an answer span from one passage (Rajpurkar et al., 2016, 2018) or multiple passages (Joshi et al., 2017; Yang et al., 2018), which is usually done by predicting the start and end positions of the an- swer (Yu et al., 2018; Devlin et al., 2018). ∗Work done during an internship at NTT. 0 1 0 1 10 weeks </s> it takes 10 weeks to get new york state tax refund . </s> Question: “how long to get nys tax refund” Generate from Voc. Copy from Question Copy from Passages Mixture weights [NLG] [Q&A] Figure 1: Visualization of how our model generates an answer on MS MARCO. Given an answer style (top: NLG, bottom: Q&A), the model controls the mixture of three distributions for generating words from a vocabulary and copying words from the ques- tion and multiple passages at each decoding step. The demand for answering questions in natural language is increasing rapidly, and this has led to the development of smart devices such as Alexa. In comparison with answer span extraction, how- ever, the natural language generation (NLG) capa- bility for RC has been less studied. While datasets such as MS MARCO (Bajaj et al., 2018) and Nar- rativeQA (Kocisk´y et al., …

Content truncated to 500 words