Complementing Lexical Retrieval with Semantic Residual Embedding

2020/04/29 by Gao, Luyu, Dai, Zhuyun, Chen, Tongfei +3 · 1 citation
#FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2004.13969

Abstract

This paper presents CLEAR, a retrieval model that seeks to complement classical lexical exact-match models such as BM25 with semantic matching signals from a neural embedding matching model. CLEAR explicitly trains the neural embedding to encode language structures and semantics that lexical retrieval fails to capture with a novel residual-based embedding learning method. Empirical evaluations demonstrate the advantages of CLEAR over state-of-the-art retrieval models, and that it can substantially improve the end-to-end accuracy and efficiency of reranking pipelines.

Cited by

• EncouRAGe: Evaluating RAG Local, Fast, and Reliable

Related

• COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
• Match Your Words! A Study of Lexical Matching in Neural Information Retrieval
• Retrieval-Enhanced Machine Learning: Synthesis and Opportunities
• Enhancing Translation Language Models with Word Embedding for Information Retrieval
• Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge