Emergency Medical Dispatch Centres (EMDC) in France are facing a growing number of calls, each requiring a rapid and efficient response, leaving no time for emergency medical dispatchers to code case files. However, this coding is essential for improving patient care through epidemiological analysis and, ultimately, for developing a decision support system. This study explores the use and deployment of natural language processing (NLP) models to automatically code records in French, based on the notes taken by call takers during emergency calls. Our work investigates fine-tuned biomedical pre-trained encoder models models for classifying highly noisy medical records, demonstrating that these models can successfully accomplish this task with a high F1 score (94%) without requiring more computationally expensive language models. To ensure the longterm reliability of the models, validation methods specifically addressing the challenges posed by EMDC data were developed. NLP can automate the coding of EMDC call records with a high degree of accuracy. However, the models currently rely solely on the written notes in the files. Future work incorporating call transcripts could further enhance their accuracy.

The application of natural language processing tools opens new ways for the documentation and revitalization of under-resourced languages. In this article we aim to investigate the feasibility of automatic part-of-speech (POS) tagging for Dagur, which is an endangered Mongolic language spoken mainly in northeast China, with no official written standard for all Dagur dialects. We present a new manually annotated corpus for Dagur, which includes about 1,200 tokens, and detail the decisions made during the annotation process. This corpus is used to test transfer of models from other languages, especially from Buryat, which is currently the only Mongolic language included in the Universal Dependencies corpora. We applied the models trained by de Vries et al. (2022) to the Dagur corpus and continued training these models on Buryat. We analyse the results with respect to language families, script and POS distribution, in three different zero-shot settings: (1) unrelated, (2) related and (3) unrelated+related language.

Parallel corpora are still scarce for most of the world’s language pairs. The situation is by no means different for regional languages of France. In addition, adequate web interfaces facilitate and encourage the use of parallel corpora by target users, such as language learners and teachers, as well as linguists. In this paper, we describe ParCoLab, a parallel corpus and a web platform for querying the corpus. From its onset, ParCoLab has been geared towards lower-resource languages, with an initial corpus in Serbian, along with French and English (later Spanish). We focus here on the extension of ParCoLab with a parallel corpus for four regional languages of France: Alsatian, Corsican, Occitan and Poitevin-Saintongeais. In particular, we detail criteria for choosing texts and issues related to their collection. The new parallel corpus contains more than 20k tokens per regional language.

In this work, we present a novel and manually corrected emotion lexicon for the Alsatian dialects, including graphical variants of Alsatian lexical items. These High German dialects are spoken in the North-East of France. They are used mainly orally, and thus lack a stable and consensual spelling convention. There has nevertheless been a continuous literary production since the middle of the 17th century and, in particular, theatre plays. A large sample of Alsatian theatre plays is currently being encoded according to the Text Encoding Initiative (TEI) Guidelines. The emotion lexicon will be used to perform automatic emotion analysis in this corpus of theatre plays. We used a graph-based approach to deriving emotion scores and translations, relying only on bilingual lexicons, cognates and spelling variants. The source lexicons for emotion scores are the NRC Valence Arousal and Dominance and NRC Emotion Intensity lexicons.

Reducing the complexity of texts by applying an Automatic Text Simplification (ATS) system has been sparking interest inthe area of Natural Language Processing (NLP) for several years and a number of methods and evaluation campaigns haveemerged targeting lexical and syntactic transformations. In recent years, several studies exploit deep learning techniques basedon very large comparable corpora. Yet the lack of large amounts of corpora (original-simplified) for French has been hinderingthe development of an ATS tool for this language. In this paper, we present our system, which is based on a combination ofmethods relying on word embeddings for lexical simplification and rule-based strategies for syntax and discourse adaptations. We present an evaluation of the lexical, syntactic and discourse-level simplifications according to automatic and humanevaluations. We discuss the performances of our system at the lexical, syntactic, and discourse levels

This paper investigates the effectiveness of 65 cohesion-based variables that are commonly used in the literature as predictive features to assess text readability. We evaluate the efficiency of these variables across narrative and informative texts intended for an audience of L2 French learners. In our experiments, we use a French corpus that has been both manually and automatically annotated as regards to co-reference and anaphoric chains. The efficiency of the 65 variables for readability is analyzed through a correlational analysis and some modelling experiments.

OBJECTIVE: This paper describes the approaches the authors developed while participating in the i2b2/VA 2010 challenge to automatically extract medical concepts and annotate assertions on concepts and relations between concepts. DESIGN: The authors'approaches rely on both rule-based and machine-learning methods. Natural language processing is used to extract features from the input texts; these features are then used in the authors' machine-learning approaches. The authors used Conditional Random Fields for concept extraction, and Support Vector Machines for assertion and relation annotation. Depending on the task, the authors tested various combinations of rule-based and machine-learning methods. RESULTS: The authors'assertion annotation system obtained an F-measure of 0.931, ranking fifth out of 21 participants at the i2b2/VA 2010 challenge. The authors' relation annotation system ranked third out of 16 participants with a 0.709 F-measure. The 0.773 F-measure the authors obtained on concept extraction did not make it to the top 10. CONCLUSION: On the one hand, the authors confirm that the use of only machine-learning methods is highly dependent on the annotated training data, and thus obtained better results for well-represented classes. On the other hand, the use of only a rule-based method was not sufficient to deal with new types of data. Finally, the use of hybrid approaches combining machine-learning and rule-based approaches yielded higher scores.

We analyze the requirements for an educational Question Answering (QA) system operating on social media content. As a result, we identify a set of advanced natural language processing (NLP) technologies to address the challenges in educational QA. We conducted an inter-annotator agreement study on subjective question classification in the Yahoo!Answers social Q&A site and propose a simple, but effective approach to automatically identify subjective questions. We also developed a two-stage QA architecture for answering learners' questions. In the first step, we aim at re-using human answers to already answered questions by employing question paraphrase identification [1]. In the second step, we apply information retrieval techniques to perform answer retrieval from social media content. We show that elaborate techniques for question preprocessing are crucial.