Diverse Multi-Answer Retrieval with Determinantal Point Processes
This addresses the need for QA systems to handle ambiguous questions with multiple interpretations, providing a domain-specific improvement for information retrieval.
The paper tackles the problem of ambiguous questions in open-domain QA by proposing a re-ranking approach using Determinantal Point Processes with BERT kernels to retrieve diverse passages capturing multiple answers, and it outperforms state-of-the-art methods on the AmbigQA dataset.
Often questions provided to open-domain question answering systems are ambiguous. Traditional QA systems that provide a single answer are incapable of answering ambiguous questions since the question may be interpreted in several ways and may have multiple distinct answers. In this paper, we address multi-answer retrieval which entails retrieving passages that can capture majority of the diverse answers to the question. We propose a re-ranking based approach using Determinantal point processes utilizing BERT as kernels. Our method jointly considers query-passage relevance and passage-passage correlation to retrieve passages that are both query-relevant and diverse. Results demonstrate that our re-ranking technique outperforms state-of-the-art method on the AmbigQA dataset.