Diverse Multi-Answer Retrieval with Determinantal Point Processes

2022/11/29 by Poojitha Nandigam, Nandigam, Poojitha, Nikhil Rayaprolu +3 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2211.16029

openalex publication_date 2022/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning

Related

• Joint Passage Ranking for Diverse Multi-Answer Retrieval
• Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering
• MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models
• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• Improving Passage Retrieval with Zero-Shot Question Generation