Coupled with the availability of large scale datasets, deep learning architectures have enabled rapid progress on Question Answering tasks. However, most of those datasets are in English, and the performances of state-of-theart multilingual models are significantly lower when evaluated on non-English data. Due to high data collection costs, it is not realistic to obtain annotated data for each language one desires to support.We propose a method to improve Crosslingual Question Answering performance without requiring additional annotated data, leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion. We show that the proposed method allows to significantly outperform the baselines trained on English data only, establishing thus a new state-of-the-art on four multilingual datasets: MLQA, XQuAD, SQuAD-it and PIAF (fr). * * : equal contribution. The work of Arij Riabi was partly carried out while she was working at reciTAL.
Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen highresource languages. Building language models and, more generally, NLP systems for nonstandardized and low-resource languages remains a challenging task. In this work, we focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data displaying a high level of variability, we compare the downstream performance of a character-based language model on part-of-speech tagging and dependency parsing to that of monolingual and multilingual models. We show that a characterbased model trained on only 99k sentences of NArabizi and fined-tuned on a small treebank of this language leads to performance close to those obtained with the same architecture pretrained on large multilingual and monolingual models. Confirming these results a on much larger data set of noisy French user-generated content, we argue that such character-based language models can be an asset for NLP in low-resource and high language variability settings.
We propose our solution to the multimodal semantic role labeling task from the CON-STRAINT'22 workshop. The task aims at classifying entities in memes into classes such as "hero" and "villain". We use several pre-trained multi-modal models to jointly encode the text and image of the memes, and implement three systems to classify the role of the entities. We propose dynamic sampling strategies to tackle the issue of class imbalance. Finally, we perform qualitative analysis on the representations of the entities. * These authors contributed equally. 1 We take each (meme, entity) pair as independent sam-
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.