Linguistics For Language Processing

The linguists of LIGM belong to the ADA team.
We work on all the chain from fundamental linguistic knowledge to information extraction and other applications.
We contribute to creating and maintaining lexical and grammatical databases.
We contribute to the Unitex/GramLab platform.
We participate in projects of information extraction, information retrieval, named entity extraction etc.



Who knows that not all light verbs are verbs?	Magritte, 1928-1929	Support verbs that are not verbs Eric Laporte, Jee-sun Nam, Jeannot Fils Ranaivoson, Takuya Nakamura, 2025, Language Sciences 111, 101741.

Just released	Univ Gustave Eiffel	Denis Maurel, Cvetana Krstev, Unitex Getting Started, 2024, Language Resources and Technology Society (JeRTeH) and University of Belgrade, 288 pages, ISBN 9798338757444.

Detecting fake news with machine learning and linguistic features	pict rider	COVID-19 Infodemic: Understanding content features in detecting fake news using a machine learning approach Vimala Balakrishnan, Lee Zing Hii, Eric Laporte, Malaysian Journal of Computer Science, 2023, 36 (1), pp. 1-13.

A multiword expression used as a discourse formula	pathdoc	C'est pour moi que tu dis ça ? Entendre une voix en sourdine et contester Christiane Marque-Pucheu, Takuya Nakamura. In Histoires de dire 3 : Petit glossaire des marqueurs formés sur le verbe dire, Peter Lang, pp. 85-109, 2023.

Building training datasets for chatbots	WrightStudio	Generating training datasets for legal chatbots in Korean Changhoe Hwang, Jee-Sun Nam, Eric Laporte. International conference on Law and Society, P. Suresh, Feb 2023, Hanoï, Vietnam, pp. 1-4.

Highlighting female creators in urban space		Cité des Dames. Créatrices dans la cité Research Grant by I-Site Future, 2019-2023

Discriminating support verb constructions from verbal idioms	Drobot Dean	L'idée nous est venue d'écrire ça pour Annibale… Complex support verb constructions with idée' Aggeliki Fotopoulou, Eric Laporte, Takuya Nakamura. Comunicazione, Linguaggi e Società. Studi in onore di Annibale Elia, Taurus, pp. 237-253, 2022.

Patent on fault-tolerant information extraction	Par U.S. government Extracted from PDF file here, Domaine public, https://commons.wikimedia.org/w/index.php?curid=2656608	US Patent no. 11386269-B2, United States Patent and Trademark Office Inventors: C. Martinez, C. Martineau, A. Schoen, T. Kyriacopoulou, 2022

What can hybrid approaches do for modern language processing?	Drobot Dean	Hybrid Language Processing in the Deep Learning Era 2022 International Conference on Natural Language and Speech Processing, keynote speech

Building a training dataset for opinion analysis	ParinPIX	SSP-based construction of evaluation-annotated data for fine-grained aspect-based sentiment analysis Suwon Choi, Shinwoo Kim, Changhoe Hwang, Gwanghoon Yoo, Eric Laporte, Jeesun Nam. COLING Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning (Pan-DL), Oct 2022, Gyeongju, South Korea, pp. 38-44.

Building training datasets for chatbots	WrightStudio	Building Korean linguistic resource for NLU data generation of banking app CS dialog system Jeongwoo Yoon, On-yu Park, Changhoe Hwang, Gwanghoon Yoo, Eric Laporte, Jeesun Nam. COLING Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning (Pan-DL), Oct 2022, Gyeongju, South Korea, pp.29-37.

Measuring the distance between two written varieties of a language		Le changement linguistique au XVIIe s. : nouvelles approches scriptométriques Simon Gabay, Rachel Bawden, Philippe Gambette, Jonathan Poinhos, Eleni Kogkitsidou, Benoît Sagot. CMLF 2022 - 8e Congrès Mondial de Linguistique Française, Jul 2022, Orléans, France, pp. 02006.1-14.