SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.01965 · 2024

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.01965")
get_code_for_paper("2407.01965")
have("2407.01965")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.01965.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.01965.svg)](https://syntology.ai/paper/2407.01965)

Connect an agent — have() is free.