Can AI Generate Love Advice?: Toward Neural Answer Generation for Non-Factoid Questions

TL;DR

This paper introduces a neural answer construction model that improves non-factoid question answering by understanding context and generating tailored answers, demonstrated through love advice datasets with significant accuracy gains.

Contribution

It presents a novel neural model that combines semantic bias integration and biLSTM-based answer generation, moving beyond simple answer selection for non-factoid questions.

Findings

Achieved 20% higher accuracy in answer creation over baselines.

Successfully applied to love advice service in Japanese QA site.

Enhances answer relevance by understanding contextual word usage.

Abstract

Deep learning methods that extract answers for non-factoid questions from QA sites are seen as critical since they can assist users in reaching their next decisions through conversations with AI systems. The current methods, however, have the following two problems: (1) They can not understand the ambiguous use of words in the questions as word usage can strongly depend on the context. As a result, the accuracies of their answer selections are not good enough. (2) The current methods can only select from among the answers held by QA sites and can not generate new ones. Thus, they can not answer the questions that are somewhat different with those stored in QA sites. Our solution, Neural Answer Construction Model, tackles these problems as it: (1) Incorporates the biases of semantics behind questions into word embeddings while also computing them regardless of the semantics. As a result, it can extract answers that suit the contexts of words used in the question as well as following the common usage of words across semantics. This improves the accuracy of answer selection. (2) Uses biLSTM to compute the embeddings of questions as well as those of the sentences often used to form answers. It then simultaneously learns the optimum combination of those sentences as well as the closeness between the question and those sentences. As a result, our model can construct an answer that corresponds to the situation that underlies the question; it fills the gap between answer selection and generation and is the first model to move beyond the current simple answer selection model for non-factoid QAs. Evaluations using datasets created for love advice stored in the Japanese QA site, Oshiete goo, indicate that our model achieves 20% higher accuracy in answer creation than the strong baselines. Our model is practical and has already been applied to the love advice service in Oshiete goo.