159 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Sorbonne UniversitéFR68 papers
- Centre National de la Recherche ScientifiqueFR66 papers
- Université Paris 1 Panthéon-SorbonneFR26 papers
- Université Paris CitéFR24 papers
- Université Paris-SaclayFR16 papers
- Université Paris Sciences et LettresFR14 papers
- École Normale Supérieure - PSLFR13 papers
- Sorbonne Paris CitéFR12 papers
- Institut de Mathématiques de Jussieu-Paris Rive GaucheFR10 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR8 papers
- CEA Paris-SaclayFR7 papers
- Institut Universitaire de FranceFR7 papers
10 papers · 1 filter
Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts
Ioana Buhnila, Georgeta Cislaru, Amalia Todirascu
Large Language Models (LLMs) have been used to generate texts in response to different writing tasks: reports, essays, story telling. However, language models do not have a meta-re…
An Incremental Clustering Baseline for Event Detection on Twitter
Marjolaine Ray, Qi Wang, Frédérique Mélanie-Becquet +2
Event detection in text streams is a crucial task for the analysis of online media and social networks. One of the current challenges in this field is establishing a performance st…
The Self-Contained Negation Test Set
David Kletz, Pascal Amsili, Marie Candito
Several methodologies have recently been proposed to evaluate the ability of Pretrained Language Models (PLMs) to interpret negation. In this article, we build on Gubelmann and Han…
Probing structural constraints of negation in Pretrained Language Models
David Kletz, Marie Candito, Pascal Amsili
Contradictory results about the encoding of the semantic impact of negation in pretrained language models (PLMs). have been drawn recently (e.g. Kassner and Sch{ü}tze (2020); Gubel…
Explainability of machine learning approaches in forensic linguistics: a case study in geolinguistic authorship profiling
Dana Roemling, Yves Scherrer, Aleksandra Miletic
Forensic authorship profiling uses linguistic markers to infer characteristics about an author of a text. This task is paralleled in dialect classification, where a prediction is m…
The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research
Mohamed Abdalla, Jan Philip Wahle, Terry Ruas +4
Recent advances in deep learning methods for natural language processing (NLP) have created new business opportunities and made NLP research critical for industry development. As o…
Technological taxonomies for hypernym and hyponym retrieval in patent texts
You Zuo, Yixuan Li, Alma Parias García +1
This paper presents an automatic approach to creating taxonomies of technical terms based on the Cooperative Patent Classification (CPC). The resulting taxonomy contains about 170k…
Probing for the Usage of Grammatical Number
Karim Lasri, Tiago Pimentel, Alessandro Lenci +2
A central quest of probing is to uncover how pre-trained models encode a linguistic property within their representations. An encoding, however, might be spurious-i.e., the model m…
Parsing Universal Dependencies without training
Héctor Martínez Alonso, Željko Agić, Barbara Plank +1
We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step de…
Automatic Detection of Reuses and Citations in Literary Texts
Jean-Gabriel Ganascia, Pierre Glaudes, Andrea Del Lungo
For more than forty years now, modern theories of literature (Compagnon, 1979) insist on the role of paraphrases, rewritings, citations, reciprocal borrowings and mutual contributi…