NLP models have been known to perform poorly on user-generated content (UGC), mainly because it presents a lot of lexical variations and deviates from the standard texts on which most of these models were trained. In this work, we focus on the robustness of LASER, a sentence embedding model, to UGC data. We evaluate this robustness by LASER’s ability to represent non-standard sentences and their standard counterparts close to each other in the embedding space. Inspired by previous works extending LASER to other languages and modalities, we propose RoLASER, a robust English encoder trained using a teacher-student approach to reduce the distances between the representations of standard and UGC sentences. We show that with training only on standard and synthetic UGC-like data, RoLASER significantly improves LASER’s robustness to both natural and artificial UGC data by achieving up to 2x and 11x better scores. We also perform a fine-grained analysis on artificial UGC data and find that our model greatly outperforms LASER on its most challenging UGC phenomena such as keyboard typos and social media abbreviations. Evaluation on downstream tasks shows that RoLASER performs comparably to or better than LASER on standard data, while consistently outperforming it on UGC data.

L’essor du traitement automatique des langues (TAL) se vit dans un monde où l’on produit de plus en plus de contenus en ligne. En particulier sur les réseaux sociaux, les textes publiés par les internautes sont remplis de phénomènes « non standards » tels que les fautes d’orthographe, l’argot, les marques d’expressivité, etc. Ainsi, les modèles de TAL, en grande partie entraînés sur des données « standards », voient leur performance diminuer lorsqu’ils sont appliqués aux contenus générés par les utilisateurs (CGU). L’une des approches pour atténuer cette dégradation est la normalisation lexicale : les mots non standards sont remplacés par leurs formes standards. Dans cet article, nous réalisons un état de l’art de la normalisation lexicale des CGU, ainsi qu’une étude expérimentale préliminaire pour montrer les avantages et les difficultés de cette tâche.

The 2022 Multilingual Representation Learning (MRL) Shared Task was dedicated to clause-level morphology. As the first ever benchmark that defines and evaluates morphology outside its traditional lexical boundaries, the shared task on multilingual clause-level morphology sets the scene for competition across different approaches to morphological modeling, with 3 clause-level sub-tasks: morphological inflection, reinflection and analysis, where systems are required to generate, manipulate or analyze simple sentences centered around a single content lexeme and a set of morphological features characterizing its syntactic clause. This year’s tasks covered eight typologically distinct languages: English, French, German, Hebrew, Russian, Spanish, Swahili and Turkish. The tasks has received submissions of four systems from three teams which were compared to two baselines implementing prominent multilingual learning methods. The results show that modern NLP models are effective in solving morphological tasks even at the clause level. However, there is still room for improvement, especially in the task of morphological analysis.

This paper describes the Inria ALMAnaCH team submission to the WMT 2022 general translation shared task. Participating in the language directions cs,ru,uk→en and cs↔uk, we experiment with the use of a dedicated Latin-script transcription convention aimed at representing all Slavic languages involved in a way that maximises character- and word-level correspondences between them as well as with the English language. Our hypothesis was that bringing the source and target language closer could have a positive impact on machine translation results. We provide multiple comparisons, including bilingual and multilingual baselines, with and without transcription. Initial results indicate that the transcription strategy was not successful, resulting in lower results than baselines. We nevertheless submitted our multilingual, transcribed models as our primary systems, and in this paper provide some indications as to why we got these negative results.