Learning to Explain: Answering Why-Questions via Rephrasing
This addresses the challenge of providing plausible why-question responses for language-based human-machine interaction, though it is incremental as it builds on existing sequence-to-sequence methods with new data.
The paper tackled the problem of generating natural language explanations for general phenomena, using automatically collected datasets to train sequence-to-sequence models, and demonstrated that their strategy produced highly plausible explanations compared to other models.
Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning. Previous work has either relied on human-curated structured knowledge bases or detailed domain representation to generate satisfactory explanations. They are also often limited to ranking pre-existing explanation choices. In our work, we contribute to the under-explored area of generating natural language explanations for general phenomena. We automatically collect large datasets of explanation-phenomenon pairs which allow us to train sequence-to-sequence models to generate natural language explanations. We compare different training strategies and evaluate their performance using both automatic scores and human ratings. We demonstrate that our strategy is sufficient to generate highly plausible explanations for general open-domain phenomena compared to other models trained on different datasets.