Recent advances in computational linguistics have undeniably led to the development of applications such as machine translation, speech recognition and synthesis, and opinion detection. However, these same advances (in terms of symbolic methods and machine learning models) can also be leveraged to facilitate linguistic analysis: for the search for generalizations and the creation of falsifiable models, as well as for the collection and management of data. For example, speech recognition techniques can be used to assist field linguists; machine translation and alignment techniques can aid in the creation of bilingual lexicons necessary for language documentation; and analysis and generation algorithms can be used to validate syntactic and lexical hypotheses. Computational linguistics offers linguists a wide range of techniques and resources that open up new perspectives. The objective of the scientific days is to promote interactions between the three major fields of computational linguistics, formal linguistics, and field linguistics, in order to foster the development of linguistic research that makes the most of new technologies.

In the continuity of LIFT, the thematic research network LIFT 2 aims to continue bringing together and engaging the community around the challenges of computational, formal, and field linguistics. To launch the second installment of this network in a positive spirit, while respecting the LIFT tradition (the first kickoff was already in Orléans), we invite you to join us on November 14 and 15, 2024, on the Orléans La Source campus.

The provisional schedule is as follows:

1. Simon Guillot, Anna Béranger and Nicolas Dugué    SeeMantics : un jeu lexical pour l'interprétabilité des vecteurs de mots    
2. Julien Bezançon, Marceau Hernandez, Félix Alié and Gaël Lejeune    « Défricher des Lettres » Annotation de Défigements dans des Tweets avec le Défricheur    
3. Sam Bigeard, Panagiotis Tsolakis, Emmanuel Vincent, Vincent Colotte, Pascale Erhart and Slim Ouni    Retour d’expérience : Whisper pour les langues régionales    
4. Iris Eshkol-Taravella, Barbedette Angèle, Vanessa Gaudray Bouju and Menel Mahamdi    Détection automatique de l’âge à partir de transcriptions de l’oral
5. Marina Seghier, Alice Millour and Jean-Yves Antoine    Propriétés linguistiques fines et interprétation des performances des systèmes pour la reconnaissance des entités nommées    
6. Alice Millour, Loïc Grobol, Mélanie Jouitteau and Jean-Yves Antoine    Yezh Ar Vro - La langue du pays : construire l’appropriation des applications de collecte    
7. Chunxiao Yan, Iris Eshkol-Taravella, Sarah De Vogué and Marianne Desmets    Outil de détection automatique des erreurs de coordination, développement et perspectives    
8. Theodorus Fransen, Federico Simone Samperi, Elisa Roma, Paolo Ruffolo and Marco Passarotti    Aligning lemmatisation approaches to construct a Linguistic Linked Open Data knowledge base for Old Irish    
9. Kpoglu Promise Dodzi    On segmented data and partial cognacy: automated cognate detection and input form    
10. Adrian Ceballos    Vers une grille macrosyntaxique en espagnol parlé    
11. Clémentine Bleuze, Fanny Ducel, Karën Fort and Maxime Amblard    "Un corpus qui fait tomber la barrière de la langue" : annotation de revendications dans des articles de TAL    
12. Kehina Manseri, Ioana-Madalina Silai, Iris Eshkol-Taravella and Georgeta Cislaru    Analysing the Dynamics of Textualisation through Writing Bursts and Pauses in French    
13. Rayan Ziane and Natasha Romanova    Pistes pour l’optimisation de modèles de parsing syntaxique    
14. Clara Rosina Fernandez, Séverine Guillaume and Guillaume Wisniewski    Automatisation de la segmentation pour la linguistique documentaire : une nouvelle évaluation des capacités multilingues des modèles neuronaux pré-entrainés de la parole