Papers by Delphine Bernhard
The ParCoLab Parallel Corpus and Its Extension to Four Regional Languages of France (2024.lrec-main)
Copied to clipboard
Dejan Stosic, Saša Marjanović, Delphine Bernhard, Myriam Bras, Laurent Kevers, Stella Retali-Medori, Marianne Vergez-Couret, Carole Werner
| Challenge: | Parallel corpora are scarce for most of the world's language pairs. |
| Approach: | They propose to extend ParCoLab with a parallel corpus for Alsatian, Corsican, Occitan and Poitevin-Saintongeais. |
| Outcome: | The proposed corpus contains more than 20k tokens per regional language. |
ELAL: An Emotion Lexicon for the Analysis of Alsatian Theatre Plays (2022.lrec-1)
Copied to clipboard
| Challenge: | a novel and manually corrected emotion lexicon is presented for Alsatian dialects . the dialects are used mainly orally and lack a stable and consensual spelling convention . |
| Approach: | They propose a novel and manually corrected emotion lexicon for Alsatian dialects . they use graphical variants of Alsalian lexical items to perform automatic emotion analysis . |
| Outcome: | The novel and manually corrected emotion lexicon is used to perform automatic emotion analysis in Alsatian theatre plays. |
POS Tagging for the Endangered Dagur Language (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study has focused on the so-called "dominant" languages, but it has not been inclusive in terms of language equality. |
| Approach: | They propose to use POS tagging to automatically annotate Dagur, an endangered Mongolic language . they use a manually annotated corpus to test transfer of models from other languages . |
| Outcome: | The proposed method can be used to document and revitalize endangered languages . the proposed model can be trained on Buryat, the only Mongolic language included in the corpus . |
HECTOR: A Hybrid TExt SimplifiCation TOol for Raw Texts in French (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing systems for automatic text simplification (ATS) focus on lexical and syntactic transformations, but there is no end-to-end system for French. |
| Approach: | They propose to use word embeddings for lexical simplification and rule-based strategies for syntax and discourse adaptations to improve the complexity of texts. |
| Outcome: | The proposed system performs at lexical, syntactic and discourse levels according to automatic and humanevaluations. |
Pronunciation Dictionaries for the Alsatian Dialects to Analyze Spelling and Phonetic Variation (L18-1)
Copied to clipboard
| Challenge: | a new study compares phonetic transcriptions of Alsatian, German and French with existing pronunciation dictionaries . Alsatic dialects do not have a standardized spelling system, despite literary history dating back to the 19th century . |
| Approach: | They propose new pronunciation dictionaries for the under-resourced Alsatian dialects . they compare them with existing phonetic transcriptions of Alsalian, German and French . |
| Outcome: | The proposed dictionaries are compared with existing phonetic transcriptions of Alsatian, German and French to examine the relationship between speech and writing. |
Corpora with Part-of-Speech Annotations for Three Regional Languages of France: Alsatian, Occitan and Picard (L18-1)
Copied to clipboard
Delphine Bernhard, Anne-Laure Ligozat, Fanny Martin, Myriam Bras, Pierre Magistry, Marianne Vergez-Couret, Lucie Steiblé, Pascale Erhart, Nabil Hathout, Dominique Huck, Christophe Rey, Philippe Reynés, Sophie Rosset, Jean Sibille, Thomas Lavergne
| Challenge: | RESTAURE project aims to develop resources and tools for three regional languages of France: Alsatian, Occitan and Picard. |
| Approach: | They describe the creation of corpora with part-of-speech annotations for Alsatian, Occitan and Picard. |
| Outcome: | The authors describe the creation of annotated corpora for Alsatian, Occitan and Picard . the project is part of the RESTAURE project, which aims to develop resources and tools for these under-resourced French regional languages. |