3 papers
cs.CL2023
Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data
Robert Litschko, Ekaterina Artemova, Barbara Plank
Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In…
cs.CL2023
A General-Purpose Multilingual Document Encoder
Onur Galoğlu, Robert Litschko, Goran Glavaš
Massively multilingual pretrained transformers (MMTs) have tremendously pushed the state of the art on multilingual NLP and cross-lingual transfer of NLP models in particular. Whil…
cs.CL2021
On Cross-Lingual Retrieval with Multilingual Text Encoders
Robert Litschko, Ivan Vulić, Simone Paolo Ponzetto +1
In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval task…