Papers by Emmanuel Morin
Building Comparable Corpora for Assessing Multi-Word Term Alignment (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to extract bilingual terminologies from corpora are limited . MWTs pose serious challenges for alignment and machine translation systems . |
| Approach: | They propose an approach to build comparable corpora and bilingual term dictionaries that evaluate bilingual term alignment in comparable corpus. |
| Outcome: | The proposed method is validated on an existing dataset and manually annotated data. |
Towards a unified framework for bilingual terminology extraction of single-word and multi-word terms (C18-1)
Copied to clipboard
| Challenge: | Existing methods for extracting bilingual terminology from comparable corpora are limited to a set of syntactic patterns. |
| Approach: | They propose a framework for aligning bilingual terms independently of term lengths . they introduce some enhancements to the context-based and neural network based approaches . |
| Outcome: | The proposed framework improves the performance of the context-based and neural network based approaches and can be adapted in specialized domains. |
Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing benchmarks evaluate biases related to individual social determinants of health (SDoH) but they overlook interactions between these factors and lack context-specific assessments. |
| Approach: | They investigated the relationship between gender and other SDoH in french patient records to determine whether LLMs rely on embedded stereotypes to make gendered decisions. |
| Outcome: | The proposed models can probe stereotypes and make gendered decisions based on the data. |
DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain (2024.lrec-main)
Copied to clipboard
Yanis Labrak, Adrien Bazoge, Oumaima El Khettari, Mickael Rouvier, Pacome Constant Dit Beaufils, Natalia Grabar, Béatrice Daille, Solen Quiniou, Emmanuel Morin, Pierre-Antoine Gourraud, Richard Dufour
| Challenge: | Existing benchmarks for pre-trained language models are limited to only a few languages . a limited number of tasks are evaluated on non-standardized protocols . |
| Approach: | They propose to aggregate diverse downstream tasks into a benchmark to assess PLMs' qualities . they evaluate 8 pre-trained masked language models on general and biomedical-specific data . |
| Outcome: | The proposed benchmark assesses pre-trained language models on 20 diversified tasks. |
Where are we in Named Entity Recognition from Speech? (2020.lrec-1)
Copied to clipboard
| Challenge: | Named entity recognition is usually made through a pipeline process that consists of processing audio and applying a NER to the audio outputs. |
| Approach: | They propose an original 3-pass approach and explore the capability of an E2E system to do structured NER. |
| Outcome: | The proposed system performs better than the current pipeline approach. |
AdminSet and AdminBERT: a Dataset and a Pre-trained Language Model to Explore the Unstructured Maze of French Administrative Documents (2025.coling-main)
Copied to clipboard
| Challenge: | Pre-trained language models are used to analyze documents but administrative texts are unstructured and do not perform well. |
| Approach: | They propose a French pre-trained language model for the administrative domain . they compare it with a general domain language model and a large language model . |
| Outcome: | The proposed model improves performance on administrative and general domains. |
Transfer Learning for a Letter-Ngrams to Word Decoder in the Context of Historical Handwriting Recognition with Scarce Resources (C18-1)
Copied to clipboard
| Challenge: | Lack of data can be an issue when beginning a new study on historical handwritten documents. |
| Approach: | They propose a character-based decoder for historical handwriting recognition on Italian Comedy Registers . they use untapped data from domains, periods, languages to obtain efficient system . |
| Outcome: | The character-based decoder can be used to learn historical handwriting on Italian Comedy registers . the results show that the system can be obtained by carefully selecting the datasets used . |
Combination of Contextualized and Non-Contextualized Layers for Lexical Substitution in French (2022.lrec-1)
Copied to clipboard
| Challenge: | Lexical substitution task requires to substitute a target word by candidates in a given context. |
| Approach: | They propose a method to find synonyms for a target word and rank them based on the context of the sentence. |
| Outcome: | The proposed method increases the BERT based system on the OOT measure but decreases on the BEST measure in the SemDis 2014 benchmark. |
Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora (C18-1)
Copied to clipboard
| Challenge: | Recent studies on bilingual lexicon extraction from specialized comparable corpora show differences in performance . lack of large specialized corporan to build efficient representations can be partially explained . |
| Approach: | They propose to use character-based embedding models to combine different embeddable models . they emphasize how character-driven embeddance models outperform other models on quality . |
| Outcome: | The proposed model outperforms other models on quality of extracted bilingual lexicons . comparable corpora are an interesting and practical alternative to parallel corporation . |
Crowdsourcing-based Annotation of the Accounting Registers of the Italian Comedy (L18-1)
Copied to clipboard
Adeline Granet, Benjamin Hervy, Geoffrey Roman-Jimenez, Marouane Hachicha, Emmanuel Morin, Harold Mouchère, Solen Quiniou, Guillaume Raschia, Françoise Rubellin, Christian Viard-Gaudin
| Challenge: | CIRESFI project aims to reassess a theatrical heritage that has often been considered inferior to that of the two major, royally-privileged theaters. |
| Approach: | They propose a double annotation system for new handwritten historical documents . crowdsourcing platform is set up to perform labeling and transcription of the documents based on budget data . |
| Outcome: | The proposed system is based on a database of 25,250 pages of registers of the Italian Comedy of the 18th century. |
DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains (2023.acl-long)
Copied to clipboard
Yanis Labrak, Adrien Bazoge, Richard Dufour, Mickael Rouvier, Emmanuel Morin, Béatrice Daille, Pierre-Antoine Gourraud
| Challenge: | Recent studies have shown that pre-trained language models improve performance on a wide range of NLP tasks. |
| Approach: | They propose to use pre-trained language models to train medical domains on French language to compare performance with specialized ones. |
| Outcome: | The proposed models can take advantage of existing biomedical models in a foreign language by further pre-training them on our targeted data. |
Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora (2020.coling-main)
Copied to clipboard
| Challenge: | Narrow specialized comparable corpora are small in size, making it difficult to build efficient models to acquire translation equivalents. |
| Approach: | They propose to use Tf-Idf and cross entropy to improve bilingual lexicon induction from specialized comparable corpora by a factor of 10 . |
| Outcome: | The proposed methods improve bilingual lexicon induction by a large margin. |
BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains (2024.findings-acl)
Copied to clipboard
Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, Richard Dufour
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable versatility in recent years, offering potential applications across specialized domains such as healthcare and medicine. |
| Approach: | They propose an open-source LLM tailored for the biomedical domain that utilizes Mistral as its foundation model and pre-trained on PubMed Central. |
| Outcome: | The proposed model outperforms existing models on a benchmark comprising 10 established medical question-answering tasks in English and is competitive with proprietary models. |