no code implementations • LREC 2022 • Amir Hazem, Merieme Bouhandi, Florian Boudin, Beatrice Daille
Automatic Term Extraction (ATE) is a key component for domain knowledge understanding and an important basis for further natural language processing applications.
no code implementations • 1 Mar 2024 • Leane Jourdan, Florian Boudin, Nicolas Hernandez, Richard Dufour
Writing a scientific article is a challenging task as it is a highly codified and specific genre, consequently proficiency in written communication is essential for effectively conveying research findings and ideas.
1 code implementation • 31 Jan 2024 • Xanh Ho, Anh Khoa Duong Nguyen, An Tuan Dao, Junfeng Jiang, Yuki Chida, Kaito Sugimoto, Huy Quoc To, Florian Boudin, Akiko Aizawa
The number of Language Models (LMs) dedicated to processing scientific text is on the rise.
1 code implementation • 29 Mar 2023 • Léane Jourdan, Florian Boudin, Richard Dufour, Nicolas Hernandez
Writing a scientific article is a challenging task as it is a highly codified genre.
1 code implementation • 22 Nov 2022 • Mael Houbre, Florian Boudin, Beatrice Daille
Keyphrase generation is the task consisting in generating a set of words or phrases that highlight the main topics of a document.
1 code implementation • 17 Aug 2021 • Florian Boudin
Our test collection and code to replicate experiments are available at https://github. com/boudinfl/acm-cr
1 code implementation • ACL 2020 • Florian Boudin, Ygor Gallina, Akiko Aizawa
Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval.
no code implementations • 28 Jun 2021 • Florian Boudin, Béatrice Daille, Evelyne Jacquey, Jian-Yun Nie
Scientific digital libraries play a critical role in the development and dissemination of scientific literature.
no code implementations • NAACL 2021 • Florian Boudin, Ygor Gallina
Neural keyphrase generation models have recently attracted much interest due to their ability to output absent keyphrases, that is, keyphrases that do not appear in the source text.
no code implementations • 18 Jun 2020 • Kenichi Iwatsuki, Florian Boudin, Akiko Aizawa
We also propose a new extraction method that utilises named entities and dependency structures to remove the non-formulaic part from a sentence.
no code implementations • LREC 2020 • Kenichi Iwatsuki, Florian Boudin, Akiko Aizawa
Formulaic expressions, such as {`}in this paper we propose{'}, are used by authors of scholarly papers to perform communicative functions; the communicative function of the present example is {`}stating the aim of the paper{'}.
no code implementations • LREC 2020 • Amir Hazem, Bouh, M{\'e}rieme i, Florian Boudin, Beatrice Daille
Automatic terminology extraction is a notoriously difficult task aiming to ease effort demanded to manually identify terms in domain-specific corpora by automatically providing a ranked list of candidate terms.
1 code implementation • 10 Mar 2020 • Ygor Gallina, Florian Boudin, Béatrice Daille
Keyphrase extraction models are usually evaluated under different, not directly comparable, experimental setups.
1 code implementation • WS 2019 • Ygor Gallina, Florian Boudin, Béatrice Daille
Keyphrase generation is the task of predicting a set of lexical units that conveys the main content of a source text.
no code implementations • JEPTALNRECITAL 2019 • Bouh, M{\'e}ri{\`e}me i, Florian Boudin, Ygor Gallina
Nous pr{\'e}sentons dans cet article la participation de l{'}{\'e}quipe TALN du LS2N {\`a} la t{\^a}che d{'}indexation de cas cliniques (t{\^a}che 1).
1 code implementation • NAACL 2018 • Florian Boudin
We propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure.
1 code implementation • COLING 2016 • Florian Boudin
We describe pke, an open source python-based keyphrase extraction toolkit.
no code implementations • COLING 2016 • Adrien Bougouin, Florian Boudin, Béatrice Daille
But they are often silent on the contrary of extraction methods that do not depend on manually built resources.
1 code implementation • WS 2016 • Florian Boudin, Hugo Mougard, Damien Cram
The SemEval-2010 benchmark dataset has brought renewed attention to the task of automatic keyphrase extraction.
no code implementations • JEPTALNRECITAL 2016 • Adrien Bougouin, Florian Boudin, Beatrice Daille
Dans cet article, nous nous int{\'e}ressons {\`a} l{'}indexation de documents de domaines de sp{\'e}cialit{\'e} par l{'}interm{\'e}diaire de leurs termes-cl{\'e}s. Plus particuli{\`e}rement, nous nous int{\'e}ressons {\`a} l{'}indexation telle qu{'}elle est r{\'e}alis{\'e}e par les documentalistes de biblioth{\`e}ques num{\'e}riques.
no code implementations • LREC 2016 • Adrien Bougouin, Sabine Barreaux, Laurent Romary, Florian Boudin, B{\'e}atrice Daille
The output keyphrases of automatic keyphrase extraction methods for test documents are typically evaluated by comparing them to manually assigned reference keyphrases.