5 papers
Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval
Robert Litschko, Ivan Vulić, Simone Paolo Ponzetto +1
Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language…
Probing Pretrained Language Models for Lexical Semantics
Ivan Vulić, Edoardo Maria Ponti, Robert Litschko +2
The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge the…
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers
Robert Litschko, Ivan Vulić, Željko Agić +1
Current methods of cross-lingual parser transfer focus on predicting the best parser for a low-resource target language globally, that is, "at treebank level". In this work, we pro…
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions
Goran Glavas, Robert Litschko, Sebastian Ruder +1
Cross-lingual word embeddings (CLEs) enable multilingual modeling of meaning and facilitate cross-lingual transfer of NLP models. Despite their ubiquitous usage in downstream tasks…
Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only
Robert Litschko, Goran Glavaš, Simone Paolo Ponzetto +1
We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. The framework leverages shared cross-lingua…