A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints

2019/08/19 by Yosi Mass, Haggai Roitman, Mass, Yosi +9
Computer Science · #Computation and Language (cs.CL) #Expert finding and Q&A systems #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1908.06780

openalex publication_date 2019/08/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths. To this end, we explore the fine-tuning of BERT in different learning-to-rank setups, comprising both point-wise and pair-wise methods, resulting in substantial improvements over the state-of-the-art. We then analyze the effectiveness of BERT for different passage lengths and suggest how to cope with large passages.

Citations

• LSTM-based Deep Learning Models for Non-factoid Answer Selection

Related

• Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering
• Exploiting Sentence-Level Representations for Passage Ranking
• Passage Re-ranking with BERT
• Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering
• Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Models