Exploiting Background Knowledge in Compact Answer Generation for Why-Questions

Abstract

This paper proposes a novel method for generating compact answers to open-domain why-questions, such as the following answer, “Because deep learning technologies were introduced,” to the question, “Why did Google’s machine translation service improve so drastically?” Although many works have dealt with why-question answering, most have focused on retrieving as answers relatively long text passages that consist of several sentences. Because of their length, such passages are not appropriate to be read aloud by spoken dialog systems and smart speakers; hence, we need to create a method that generates compact answers. We developed a novel neural summarizer for this compact answer generation task. It combines a recurrent neural network-based encoderdecoder model with stacked convolutional neural networks and was designed to effectively exploit background knowledge, in this case a set of causal relations (e.g., “[Microsoft’s machine translation has made great progress over the last few years]effect since [it started to use deep learning.]cause”) that was extracted from a large web data archive (4 billion web pages). Our experimental results show that our method achieved significantly better ROUGE F-scores than existing encoder-decoder models and their variations that were augmented with query-attention and memory networks, which are used to exploit the background knowledge.

Answer Generation for Retrieval-based Question Answering Systems

“…Our approach builds on top of this line of work by designing and testing generative models for AS2-based QA systems. In recent years, the use of generative approaches has been evaluated for other QA tasks, such as machine reading (MR) (Izacard and Grave, 2021;Lewis et al, 2020b) and question-based summarization (QS) (Iida et al, 2019;Goodwin et al, 2020;Deng et al, 2020). However, while related, these efforts are fundamentally different from the experimental setting described in this paper.…”

Multi-hop Inference for Question-driven Summarization

“…Fan et al (2019) propose a multi-task Seq2Seq model with the concatenation of the question and support documents to generate long-form answers. Iida et al (2019) and Nakatsuji and Okui (2020) incorporate some background knowledge into Seq2Seq model for why questions and conclusion-centric questions. Some latest works (Feldman and El-Yaniv, 2019;Yadav et al, 2019;Nishida et al, 2019a) attempt to provide evidence or justifications for humanunderstandable explanation of the multi-hop inference process in factoid QA, where the inferred evidences are only treated as the middle steps for finding the answer.…”

Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts

“…On top of BASE, it additionally used real-representation generator R to encode compact answers, which were generated by the compactanswer generator of Iida et al (2019). R was trained alongside the why-QA model using W hySet and the compact-answer generator was pre-trained with CmpAns.…”

“…On top of BASE, it additionally used the encoder in the compact-answer generator of Iida et al (2019) to create compact-answer representation.…”

“…If we can use such automatically generated compact-answers to support a why-QA method in finding the exact reason of a whyquestion in these passages, why-QA accuracy may be improved. We actually tried this idea in a preliminary study in which we generated a compact answer from a given question-passage pair by using the compact-answer generation method of Iida et al (2019) and used the generated compactanswer along with the given question-passage pair to find proper answer passages. However, we were disappointed by the small performance improvement, as shown in our experimental results.…”