Improving Conversational Passage Re-ranking with View Ensemble

PROCEEDINGS OF THE 46TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2023(2023)

引用 0|浏览51
暂无评分
摘要
This paper presents ConvRerank, a conversational passage re-ranker that employs a newly developed pseudo-labeling approach. Our proposed view-ensemble method enhances the quality of pseudo-labeled data, thus improving the fine-tuning of ConvRerank. Our experimental evaluation on benchmark datasets shows that combining ConvRerank with a conversational dense retriever in a cascaded manner achieves a good balance between effectiveness and efficiency. Compared to baseline methods, our cascaded pipeline demonstrates lower latency and higher top-ranking effectiveness. Furthermore, the in-depth analysis confirms the potential of our approach to improving the effectiveness of conversational search.
更多
查看译文
关键词
conversational search,pseudo-labeling,passage re-ranking
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