Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment

Yilong Lai, Jialong Wu, Congzhi Zhang, Haowen Sun, Deyu Zhou

TL;DR

Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework, offering both quantitative and qualitative improvements in conversational query reformulation.

Abstract

Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context. Recent works aimed to boost the performance of CQR through alignment. However, they are designed for one specific retrieval system, which potentially results in sub-optimal generalization. To overcome this limitation, we present a novel framework AdaCQR. By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries among diverse retrieval environments through a two-stage training strategy. Moreover, two effective approaches are proposed to obtain superior labels and diverse input candidates, boosting the efficiency and robustness of the framework. Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework, offering both quantitative and qualitative improvements in conversational query reformulation.

AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment

TL;DR

Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework, offering both quantitative and qualitative improvements in conversational query reformulation.

Abstract

Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context. Recent works aimed to boost the performance of CQR through alignment. However, they are designed for one specific retrieval system, which potentially results in sub-optimal generalization. To overcome this limitation, we present a novel framework AdaCQR. By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries among diverse retrieval environments through a two-stage training strategy. Moreover, two effective approaches are proposed to obtain superior labels and diverse input candidates, boosting the efficiency and robustness of the framework. Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework, offering both quantitative and qualitative improvements in conversational query reformulation.
Paper Structure (42 sections, 7 equations, 3 figures, 18 tables)

This paper contains 42 sections, 7 equations, 3 figures, 18 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Conversational Search
  4. Aligning LMs using Feedback
  5. Method
  6. Task Formulation
  7. Overall Framework
  8. Fusion Metric for Sparse and Dense Retrieval
  9. Superior Reformulation Annotation
  10. Align LMs with Retrievers
  11. Training Stage 1 for Initialization
  12. Candidates Generation for Alignment
  13. Training Stage 2 for Alignment
  14. Experiments
  15. Datasets
  16. ...and 27 more sections

Figures (3)

  • Figure 1: An example of CQR which takes the context and current query as input and generates a decontextualized query as output.
  • Figure 2: The framework of the proposed AdaCQR. A two-stage training is employed, where Stage 1 involves minimizing generation loss $\mathcal{L}_g$, followed by Stage 2 employing contrastive loss $\mathcal{L}_c$. The evaluation score is a distribution vector defined in Eq. \ref{['eq:reference-free-evaluation-score']}.
  • Figure 3: Analysis of the aligned reformulation query across epochs in Stage 2 training, focusing on the term overlap (DICE coefficient) and semantic similarity with the gold passage (cosine similarity).