Emergence of Syntax Needs Minimal Supervision

no code implementations • ACL 2020 • Rapha{\"e}l Bailly, Kata G{\'a}bor

This paper is a theoretical contribution to the debate on the learnability of syntax from a corpus without explicit syntax-specific guidance.

SemEval-2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers

no code implementations • SEMEVAL 2018 • Kata G{\'a}bor, Davide Buscaldi, Anne-Kathrin Schumann, Behrang Qasemizadeh, Ha{\"\i}fa Zargayouna, Thierry Charnois

This paper describes the first task on semantic relation extraction and classification in scientific paper abstracts at SemEval 2018.

Classification General Classification +3

Apport des d\'ependances syntaxiques et des patrons s\'equentiels \`a l'extraction de relations ()

no code implementations • JEPTALNRECITAL 2018 • Kata G{\'a}bor, Nad{\`e}ge Lechevrel, Isabelle Tellier, Davide Buscaldi, Haifa Zargayouna, Thierry Charnois

Exploring Vector Spaces for Semantic Relations

no code implementations • EMNLP 2017 • Kata G{\'a}bor, Ha{\"\i}fa Zargayouna, Isabelle Tellier, Davide Buscaldi, Thierry Charnois

Word embeddings are used with success for a variety of tasks involving lexical semantic similarities between individual words.

Clustering General Classification +3

D\'etection et classification non supervis\'ees de relations s\'emantiques dans des articles scientifiques (Unsupervised Classification of Semantic Relations in Scientific Papers)

no code implementations • JEPTALNRECITAL 2016 • Kata G{\'a}bor, Isabelle Tellier, Thierry Charnois, Ha{\"\i}fa Zargayouna, Davide Buscaldi

Une analyse manuelle nous a permis de proposer une typologie des relations s{\'e}mantiques, et de classifier un {\'e}chantillon d{'}instances de relations.

Classification Clustering +1

Semantic Annotation of the ACL Anthology Corpus for the Automatic Analysis of Scientific Literature

no code implementations • LREC 2016 • Kata G{\'a}bor, Ha{\"\i}fa Zargayouna, Davide Buscaldi, Isabelle Tellier, Thierry Charnois

This paper describes the process of creating a corpus annotated for concepts and semantic relations in the scientific domain.

Relation Classification

Named Entity Recognition and Correction in OCRized Corpora (D\'etection et correction automatique d'entit\'es nomm\'ees dans des corpus OCRis\'es) [in French]

no code implementations • JEPTALNRECITAL 2014 • Beno{\^\i}t Sagot, Kata G{\'a}bor

named-entity-recognition Named Entity Recognition +2

The WoDiS System - WOlf and DIStributions for Lexical Substitution (Le syst\`eme WoDiS - WOLF et DIStributions pour la substitution lexicale) [in French]

no code implementations • JEPTALNRECITAL 2014 • Kata G{\'a}bor

Document Classification Word Sense Disambiguation

Automated Error Detection in Digitized Cultural Heritage Documents

no code implementations • WS 2014 • Kata G{\'a}bor, Beno{\^\i}t Sagot

Optical Character Recognition (OCR) Spelling Correction

Boosting the Coverage of a Semantic Lexicon by Automatically Extracted Event Nominalizations

no code implementations • LREC 2012 • Kata G{\'a}bor, Marianna Apidianaki, Beno{\^\i}t Sagot, {\'E}ric Villemonte de la Clergerie

In this article, we present a distributional analysis method for extracting nominalization relations from monolingual corpora.

Word Sense Induction