Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

5-2024

Abstract

Question-answering (QA) retrieval is the task of retrieving the most relevant answer to a given question from a collection of answers. Various approaches to QA retrieval have been developed recently. One successful and popular model is Contextualized Late Interaction over BERT (ColBERT), a transformer-based approach that adopts a query-document scoring mechanism that retains the granularity of transformer matching, whilst improving on efficiency. However, one key limitation is that it requires further fine-tuning for new query or collection types. In this work, we explore and propose several non-parametric retrieval augmentation methods based on explicit signals of term importance that improve over ColBERT's baseline performance. In particular, we consider the QA retrieval task in the context of StackExchange question-answering forum, verifying the effectiveness of our methods in this setting.

Keywords

Information retrieval, Retrieval models, Retrieval ranking, Question-answering, Neural information retrieval, Term importance, Weighted late interaction

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

Proceedings of the ACM Web Conference 2024 (WWW 2024) : Singapore, May 13-17

First Page

601

Last Page

604

Identifier

10.1145/3589335.3651568

Publisher

Association for Computing Machinery

City or Country

Singapore

Comments

PDF provided by faculty

Additional URL

https://doi.org/10.1145/3589335.3651568

Download

Share

COinS