What a great finish to have my last two PhD papers accepted at the International Conference on Computational Linguistics (COLING):

1️⃣ “Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain”, where I study the efficacy of hybrid search across a variety of prominent retrieval models within the unexplored field of law in the French language, assessing both zero-shot and in-domain scenarios.

    📄 Paper     |     🤗 Models    |     💻 Code    |     🧵 TL;DR

2️⃣ “ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval”, where I present a modular dense retrieval model that learns from a single high-resource language (like English) and effectively transfers zero-shot to other languages, thereby eliminating the need for language-specific labeled retrieval data.

    📄 Paper     |     🤗 Model    |     💻 Code    |     🧵 TL;DR