DeepAI AI Chat
Log In Sign Up

Improving Conversational Passage Re-ranking with View Ensemble

by   Jia-Huei Ju, et al.

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.


page 1

page 2

page 3

page 4


Submitting surveys via a conversational interface: an evaluation of user acceptance and approach effectiveness

Conversational interfaces are currently on the rise: more and more appli...

Common Conversational Community Prototype: Scholarly Conversational Assistant

This paper discusses the potential for creating academic resources (tool...

Zero-shot Query Contextualization for Conversational Search

Current conversational passage retrieval systems cast conversational sea...

A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge

This paper presents the participation of NTES_ALONG team for the ClariQ ...

Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task

In this paper, we present our submission to the sentence-level MQM bench...