arXiv
Open Access
2020
A White Box Analysis of ColBERT
Thibault Formal
Benjamin Piwowarski
Stéphane Clinchant
Abstrak
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.
Topik & Kata Kunci
Penulis (3)
T
Thibault Formal
B
Benjamin Piwowarski
S
Stéphane Clinchant
Akses Cepat
Informasi Jurnal
- Tahun Terbit
- 2020
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓