no code implementations • LREC (BUCC) 2022 • Martin Laville, Emmanuel Morin, Phillippe Langlais
With numerous new methods proposed recently, the evaluation of Bilingual Lexicon Induction have been quite hazardous and inconsistent across works.
no code implementations • COLING 2020 • Shivendra Bhardwaj, David Alfonso Hermelo, Phillippe Langlais, Gabriel Bernier-Colborne, Cyril Goutte, Michel Simard
Deep neural models tremendously improved machine translation.
no code implementations • COLING 2020 • Martin Laville, Amir Hazem, Emmanuel Morin, Phillippe Langlais
In this paper, we contrast several data selection techniques to improve bilingual lexicon induction from specialized comparable corpora.
no code implementations • LREC 2020 • Gabriel Bernier-Colborne, Phillippe Langlais
To assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or ambiguity.
1 code implementation • LREC 2020 • Abbas Ghaddar, Phillippe Langlais
This paper describes the acquisition, preprocessing and characteristics of SEDAR, a large scale English-French parallel corpus for the financial domain.
no code implementations • WS 2019 • Abbas Ghaddar, Phillippe Langlais
We describe a special type of deep contextualized word representation that is learned from distant supervision annotations and dedicated to named entity recognition.
no code implementations • IJCNLP 2017 • Abbas Ghaddar, Phillippe Langlais
We revisit the idea of mining Wikipedia in order to generate named-entity annotations.
no code implementations • WS 2017 • Phillippe Langlais
Despite numerous studies devoted to mining parallel material from bilingual data, we have yet to see the resulting technologies wholeheartedly adopted by professional translators and terminologists alike.
no code implementations • EACL 2017 • Laurent Jakubina, Phillippe Langlais
We investigate the reranking of the output of several distributional approaches on the Bilingual Lexicon Induction task.
no code implementations • LREC 2016 • Abbas Ghaddar, Phillippe Langlais
This paper presents WikiCoref, an English corpus annotated for anaphoric relations, where all documents are from the English version of Wikipedia.
no code implementations • LREC 2014 • Fabrizio Gotti, Phillippe Langlais, Atefeh Farzindar
A manual analysis of the bilingual alignment of 5000 hashtags shows that 5{\%} (French) to 18{\%} (English) of them don{'}t have a counterpart in their containing tweet{'}s translation.
no code implementations • LREC 2014 • Lise Rebout, Phillippe Langlais
We describe an approach for mining parallel sentences in a collection of documents in two languages.