Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
Conference of the European Chapter of the Association for Computational Linguistics(2023)
摘要
The long-standing goal of dense retrievers in abtractive open-domain question
answering (ODQA) tasks is to learn to capture evidence passages among relevant
passages for any given query, such that the reader produce factually correct
outputs from evidence passages. One of the key challenge is the insufficient
amount of training data with the supervision of the answerability of the
passages. Recent studies rely on iterative pipelines to annotate answerability
using signals from the reader, but their high computational costs hamper
practical applications. In this paper, we instead focus on a data-centric
approach and propose Evidentiality-Aware Dense Passage Retrieval (EADPR), which
leverages synthetic distractor samples to learn to discriminate evidence
passages from distractors. We conduct extensive experiments to validate the
effectiveness of our proposed method on multiple abstractive ODQA tasks.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要