Conclusion-Supplement Answer Generation for Non-Factoid Questions
This work tackles a critical issue in NLP and AI for users requiring detailed answers to non-factoid questions, representing an incremental improvement over existing encoder-decoder frameworks.
The paper addresses the challenge of generating conclusion-supplement answers for non-factoid questions, where users need supplementary information, and proposes an ensemble network that fuses conclusion and supplementary statements using attention mechanisms, resulting in more accurate outputs compared to baselines on datasets like 'Love Advice' and 'Arts & Humanities'.
This paper tackles the goal of conclusion-supplement answer generation for non-factoid questions, which is a critical issue in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI), as users often require supplementary information before accepting a conclusion. The current encoder-decoder framework, however, has difficulty generating such answers, since it may become confused when it tries to learn several different long answers to the same non-factoid question. Our solution, called an ensemble network, goes beyond single short sentences and fuses logically connected conclusion statements and supplementary statements. It extracts the context from the conclusion decoder's output sequence and uses it to create supplementary decoder states on the basis of an attention mechanism. It also assesses the closeness of the question encoder's output sequence and the separate outputs of the conclusion and supplement decoders as well as their combination. As a result, it generates answers that match the questions and have natural-sounding supplementary sequences in line with the context expressed by the conclusion sequence. Evaluations conducted on datasets including "Love Advice" and "Arts & Humanities" categories indicate that our model outputs much more accurate results than the tested baseline models do.