no code implementations • JEP/TALN/RECITAL 2021 • Léon-Paul Schaub, Vojtech Hudecek, Daniel Stancl, Ondrej Dusek, Patrick Paroubek
Définition et détection des incohérences du système dans les dialogues orientés tâche.
1 code implementation • LREC 2022 • Vojtěch Hudeček, Leon-paul Schaub, Daniel Stancl, Patrick Paroubek, Ondřej Dušek
In this paper, we present a new dataset, obtained by merging four publicly available annotated corpora for task-oriented dialogues in several domains (MultiWOZ 2. 2, CamRest676, DSTC2 and Schema-Guided Dialogue Dataset).
no code implementations • LEGAL (LREC) 2022 • Victoria Arranz, Khalid Choukri, Montse Cuadros, Aitor García Pablos, Lucie Gianola, Cyril Grouin, Manuel Herranz, Patrick Paroubek, Pierre Zweigenbaum
This paper presents the outcomes of the MAPA project, a set of annotated corpora for 24 languages of the European Union and an open-source customisable toolkit able to detect and substitute sensitive information in text documents from any domain, using state-of-the art, deep learning-based named entity recognition techniques.
no code implementations • JEP/TALN/RECITAL 2022 • Thomas Gerald, Sofiane Ettayeb, Ha Quang Le, Anne Vilnat, Gabriel Illouz, Patrick Paroubek
Dans cette démonstration, nous présenterons les travaux en cours pour l’annotation d’un nouveau corpus de questions-réponses en langue Française.
no code implementations • EAMT 2020 • Ēriks Ajausks, Victoria Arranz, Laurent Bié, Aleix Cerdà-i-Cucó, Khalid Choukri, Montse Cuadros, Hans Degroote, Amando Estela, Thierry Etchegoyhen, Mercedes García-Martínez, Aitor García-Pablos, Manuel Herranz, Alejandro Kohan, Maite Melero, Mike Rosner, Roberts Rozis, Patrick Paroubek, Artūrs Vasiļevskis, Pierre Zweigenbaum
We describe the MAPA project, funded under the Connecting Europe Facility programme, whose goal is the development of an open-source de-identification toolkit for all official European Union languages.
no code implementations • EMNLP (ECONLP) 2021 • Jiahui Hu, Patrick Paroubek
In this paper, we present our pre-annotation models and evaluations of their performance, introduce our annotation scheme and report on the main characteristics of our corpus.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
no code implementations • 4 Sep 2024 • Mathieu Laï-king, Patrick Paroubek
Domain adaptation is a widely used method in natural language processing (NLP) to improve the performance of a language model within a specific domain.
2 code implementations • 27 Mar 2024 • Lisa Raithel, Hui-Syuan Yeh, Shuntaro Yada, Cyril Grouin, Thomas Lavergne, Aurélie Névéol, Patrick Paroubek, Philippe Thomas, Tomohiro Nishiyama, Sebastian Möller, Eiji Aramaki, Yuji Matsumoto, Roland Roller, Pierre Zweigenbaum
User-generated data sources have gained significance in uncovering Adverse Drug Reactions (ADRs), with an increasing number of discussions occurring in the digital world.
1 code implementation • 23 Feb 2024 • Armand Stricker, Patrick Paroubek
During task-oriented dialogues (TODs), human users naturally introduce chitchat that is beyond the immediate scope of the task, interfering with the flow of the conversation.
1 code implementation • 24 Jan 2024 • Armand Stricker, Patrick Paroubek
In current text-based task-oriented dialogue (TOD) systems, user emotion detection (ED) is often overlooked or is typically treated as a separate and independent task, requiring additional training.
no code implementations • 23 Nov 2023 • Armand Stricker, Patrick Paroubek
Most existing dialogue corpora and models have been designed to fit into 2 predominant categories : task-oriented dialogues portray functional goals, such as making a restaurant reservation or booking a plane ticket, while chit-chat/open-domain dialogues focus on holding a socially engaging talk with a user.
1 code implementation • 23 Nov 2023 • Armand Stricker, Patrick Paroubek
As a recent development, task-oriented dialogues (TODs) have been enriched with chitchat in an effort to make dialogues more diverse and engaging.
no code implementations • 15 May 2023 • Gustave Cortal, Alain Finkel, Patrick Paroubek, Lina Ye
Emotion regulation is a crucial element in dealing with emotional events and has positive effects on mental health.
no code implementations • 11 Oct 2022 • Gustave Cortal, Alain Finkel, Patrick Paroubek, Lina Ye
Emotion analysis in texts suffers from two major limitations: annotated gold-standard corpora are mostly small and homogeneous, and emotion identification is often simplified as a sentence-level classification problem.
no code implementations • WS 2020 • Anna Koroleva, Sanjay Kamath, Patrick Bossuyt, Patrick Paroubek
The proposed tool is the first tool for spin detection.
no code implementations • LREC 2020 • Corentin Masson, Patrick Paroubek
Recent advances in neural computing and word embeddings for semantic processing open many new applications areas which had been left unaddressed so far because of inadequate language understanding capacity.
no code implementations • WS 2019 • Anna Koroleva, Patrick Paroubek
Statistical hypothesis testing is used to test if the experimental intervention is superior to the control.
no code implementations • JEPTALNRECITAL 2018 • Patrick Paroubek, Cyril Grouin, Patrice Bellot, Vincent Claveau, Iris Eshkol-Taravella, Amel Fraisse, Agata Jackiewicz, Jihen Karoui, Laura Monceaux, Juan-Manuel Torres-Moreno
Cet article pr{\'e}sente l{'}{\'e}dition 2018 de la campagne d{'}{\'e}valuation DEFT (D{\'e}fi Fouille de Textes).
no code implementations • WS 2016 • Gil Francopoulo, Joseph Mariani, Patrick Paroubek, Fr{\'e}d{\'e}ric Vernier
By its own nature, the Natural Language Processing (NLP) community is a priori the best equipped to study the evolution of its own publications, but works in this direction are rare and only recently have we seen a few attempts at charting the field.
Named Entity Recognition (NER)
Optical Character Recognition (OCR)
no code implementations • JEPTALNRECITAL 2016 • Paul Bui-Quang, Brigitte Grau, Patrick Paroubek
AppFM 1 est un outil {\`a} mi-chemin entre un environnement de cr{\'e}ation de cha{\^\i}nes modulaires de TAL et un gestionnaire de services syst{\`e}mes.
no code implementations • LREC 2016 • Gil Francopoulo, Joseph Mariani, Patrick Paroubek
The aim of this experiment is to present an easy way to compare fragments of texts in order to detect (supposed) results of copy {\&} paste operations between articles in the domain of Natural Language Processing (NLP).
no code implementations • LREC 2016 • Gil Francopoulo, Joseph Mariani, Patrick Paroubek
Predictive modeling, often called {``}predictive analytics{''} in a commercial context, encompasses a variety of statistical techniques that analyze historical and present facts to make predictions about unknown events.
no code implementations • JEPTALNRECITAL 2015 • Amel Fraisse, Patrick Paroubek
Des travaux en analyse de sentiments ont montr{\'e} l{'}int{\'e}r{\^e}t des {\'e}motic{\^o}nes et r{\'e}cemment des mots-di{\`e}ses, qui s{'}av{\`e}rent {\^e}tre tr{\`e}s utiles pour la classification en polarit{\'e}.
no code implementations • JEPTALNRECITAL 2014 • Thierry Hamon, Quentin Plepl{\'e}, Patrick Paroubek, Pierre Zweigenbaum, Cyril Grouin
no code implementations • LREC 2014 • Munshi Asadullah, Patrick Paroubek, Anne Vilnat
We shall illustrate the mapping of important syntactic phenomena using the corpus made of the examples of the FTB - DEP annotation guidelines, which we have hand-annotated with PASSAGE annotations and used to compute quantitative performance measures on the FTB - DEP guidelines. n this paper we will briefly introduce the two annotation formats.
no code implementations • LREC 2014 • Joseph Mariani, Christopher Cieri, Gil Francopoulo, Patrick Paroubek, Marine Delaborde
This paper describes the problems that must be addressed when studying large amounts of data over time which require entity normalization applied not to the usual genres of news or political speech, but to the genre of academic discourse about language resources, technologies and sciences.
no code implementations • LREC 2014 • Joseph Mariani, Patrick Paroubek, Gil Francopoulo, Olivier Hamon
It follows similar exercises that have been conducted, such as the survey on the IEEE ICASSP conference series from 1976 to 1990, which served in the launching of the ESCA Eurospeech conference, a survey of the Association of Computational Linguistics (ACL) over 50 years of existence, which was presented at the ACL conference in 2012, or a survey over the 25 years (1987-2012) of the conferences contained in the ISCA Archive, presented at Interspeech 2013.
no code implementations • LREC 2014 • Amel Fraisse, Patrick Paroubek
This paper presents a logical formalization of a set 20 semantic categories related to opinion, emotion and sentiment.
no code implementations • JEPTALNRECITAL 2012 • Patrick Paroubek, Pierre Zweigenbaum, Dominic Forest, Cyril Grouin
no code implementations • LREC 2012 • Patrick Paroubek, Xavier Tannier
In this paper, we present the founding elements of a formal model of the evaluation paradigm in natural language processing.