A White Box Analysis of ColBERT

12/17/2020
by   Thibault Formal, et al.
0

Transformer-based models are nowadays state-of-the-art in ad-hoc Information Retrieval, but their behavior is far from being understood. Recent work has claimed that BERT does not satisfy the classical IR axioms. However, we propose to dissect the matching process of ColBERT, through the analysis of term importance and exact/soft matching patterns. Even if the traditional axioms are not formally verified, our analysis reveals that ColBERT: (i) is able to capture a notion of term importance; (ii) relies on exact matches for important terms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/23/2017

A Deep Relevance Matching Model for Ad-hoc Retrieval

In recent years, deep neural networks have led to exciting breakthroughs...
research
01/28/2021

A Graph-based Relevance Matching Model for Ad-hoc Retrieval

To retrieve more relevant, appropriate and useful documents given a quer...
research
12/10/2021

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

Neural Information Retrieval models hold the promise to replace lexical ...
research
08/15/2022

Continuous Active Learning Using Pretrained Transformers

Pre-trained and fine-tuned transformer models like BERT and T5 have impr...
research
01/12/2022

Diagnosing BERT with Retrieval Heuristics

Word embeddings, made widely popular in 2013 with the release of word2ve...
research
03/26/2019

Simple Applications of BERT for Ad Hoc Document Retrieval

Following recent successes in applying BERT to question answering, we ex...

Please sign up or login with your details

Forgot password? Click here to reset