Match Your Words! A Study of Lexical Matching in Neural Information Retrieval

• Main Authors: Formal, Thibault, Piwowarski, Benjamin, Clinchant, Stéphane
• Format: Journal Article
• Language: English
• Published: 10.12.2021
• Subjects: Computer Science - Computation and Language; Computer Science - Information Retrieval
• DOI: 10.48550/arxiv.2112.05662

Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged on out-of-domain zero-shot settings (BEIR benchmark), questioning their actual generalization capabilities compared to bag-of-words approaches. Particularly, we wonder if these shortcomings could (partly) be the consequence of the inability of neural IR models to perform lexical matching off-the-shelf. In this work, we propose a measure of discrepancy between the lexical matching performed by any (neural) model and an 'ideal' one. Based on this, we study the behavior of different state-of-the-art neural IR models, focusing on whether they are able to perform lexical matching when it's actually useful, i.e. for important terms. Overall, we show that neural IR models fail to properly generalize term importance on out-of-domain collections or terms almost unseen during training