Yannick Toussaint

Félix Gaschi, Patricio Cerda, Parisa Rastin et al.

Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build similar representations for pairs of words from translated sentences. But such realignment methods were found to not always improve results across languages and tasks, which raises the question of whether aligned representations are truly beneficial for cross-lingual transfer. We provide evidence that alignment is actually significantly correlated with cross-lingual transfer across languages, models and random seeds. We show that fine-tuning can have a significant impact on alignment, depending mainly on the downstream task and the model. Finally, we show that realignment can, in some instances, improve cross-lingual transfer, and we identify conditions in which realignment methods provide significant improvements. Namely, we find that realignment works better on tasks for which alignment is correlated with cross-lingual transfer when generalizing to a distant language and with smaller models, as well as when using a bilingual dictionary rather than FastAlign to extract realignment pairs. For example, for POS-tagging, between English and Arabic, realignment can bring a +15.8 accuracy improvement on distilmBERT, even outperforming XLM-R Large by 1.7. We thus advocate for further research on realignment methods for smaller multilingual models as an alternative to scaling.

Xavier Fontaine, Félix Gaschi, Parisa Rastin et al.

Natural language tasks like Named Entity Recognition (NER) in the clinical domain on non-English texts can be very time-consuming and expensive due to the lack of annotated data. Cross-lingual transfer (CLT) is a way to circumvent this issue thanks to the ability of multilingual large language models to be fine-tuned on a specific task in one language and to provide high accuracy for the same task in another language. However, other methods leveraging translation models can be used to perform NER without annotated data in the target language, by either translating the training set or test set. This paper compares cross-lingual transfer with these two alternative methods, to perform clinical NER in French and in German without any training data in those languages. To this end, we release MedNERF a medical NER test set extracted from French drug prescriptions and annotated with the same guidelines as an English dataset. Through extensive experiments on this dataset and on a German medical dataset (Frei and Kramer, 2021), we show that translation-based methods can achieve similar performance to CLT but require more care in their design. And while they can take advantage of monolingual clinical language models, those do not guarantee better results than large general-purpose multilingual models, whether with cross-lingual transfer or translation.

Félix Gaschi, François Plesse, Parisa Rastin et al.

Some Transformer-based models can perform cross-lingual transfer learning: those models can be trained on a specific task in one language and give relatively good results on the same task in another language, despite having been pre-trained on monolingual tasks only. But, there is no consensus yet on whether those transformer-based models learn universal patterns across languages. We propose a word-level task-agnostic method to evaluate the alignment of contextualized representations built by such models. We show that our method provides more accurate translated word pairs than previous methods to evaluate word-level alignment. And our results show that some inner layers of multilingual Transformer-based models outperform other explicitly aligned representations, and even more so according to a stricter definition of multilingual alignment.

Walid Hafiane, Joel Legrand, Yannick Toussaint et al.

Relation extraction (RE) consists in identifying and structuring automatically relations of interest from texts. Recently, BERT improved the top performances for several NLP tasks, including RE. However, the best way to use BERT, within a machine learning architecture, and within a transfer learning strategy is still an open question since it is highly dependent on each specific task and domain. Here, we explore various BERT-based architectures and transfer learning strategies (i.e., frozen or fine-tuned) for the task of biomedical RE on two corpora. Among tested architectures and strategies, our *BERT-segMCNN with finetuning reaches performances higher than the state-of-the-art on the two corpora (1.73 % and 32.77 % absolute improvement on ChemProt and PGxCorpus corpora respectively). More generally, our experiments illustrate the expected interest of fine-tuning with BERT, but also the unexplored advantage of using structural information (with sentence segmentation), in addition to the context classically leveraged by BERT.