Diverse Multi-Answer Retrieval with Determinantal Point Processes

TL;DR

This paper introduces a re-ranking approach using Determinantal Point Processes with BERT to retrieve diverse, relevant passages for ambiguous questions, improving multi-answer retrieval in open-domain QA systems.

Contribution

It presents a novel re-ranking method leveraging DPPs and BERT to enhance diversity and relevance in multi-answer retrieval for ambiguous questions.

Findings

Outperforms state-of-the-art on AmbigQA dataset

Effectively captures diverse answers for ambiguous questions

Improves relevance and diversity in passage retrieval

Abstract

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.