Search Results for author: Carlos Ramisch

Found 40 papers, 3 papers with code

Seen2Unseen at PARSEME Shared Task 2020: All Roads do not Lead to Unseen Verb-Noun VMWEs

no code implementations COLING (MWE) 2020 Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine

We describe the Seen2Unseen system that participated in edition 1. 2 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs).

Translation

SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings

no code implementations COLING 2020 Cindy Aloui, Carlos Ramisch, Alexis Nasr, Lucie Barque

Contextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances.

Verbal Multiword Expression Identification: Do We Need a Sledgehammer to Crack a Nut?

no code implementations COLING 2020 Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine

Automatic identification of multiword expressions (MWEs), like {`}to cut corners{'} (to do an incomplete job), is a pre-requisite for semantically-oriented downstream applications.

To Be or Not To Be a Verbal Multiword Expression: A Quest for Discriminating Features

no code implementations22 Jul 2020 Caroline Pasquer, Agata Savary, Jean-Yves Antoine, Carlos Ramisch, Nicolas Labroche, Arnaud Giacometti

We use this fact to determine the optimal set of features which could be used in a supervised classification setting to solve a subproblem of VMWE identification: the identification of occurrences of previously seen VMWEs.

Without lexicons, multiword expression identification will never fly: A position statement

no code implementations WS 2019 Agata Savary, Silvio Cordeiro, Carlos Ramisch

Because most multiword expressions (MWEs), especially verbal ones, are semantically non-compositional, their automatic identification in running text is a prerequisite for semantically-oriented downstream applications.

The Impact of Word Representations on Sequential Neural MWE Identification

no code implementations WS 2019 Nicolas Zampieri, Carlos Ramisch, Geraldine Damnati

Recent initiatives such as the PARSEME shared task allowed the rapid development of MWE identification systems.

Unsupervised Compositionality Prediction of Nominal Compounds

no code implementations CL 2019 Silvio Cordeiro, Aline Villavicencio, Marco Idiart, Carlos Ramisch

General crosslingual analyses reveal the impact of morphological variation and corpus size in the ability of the model to predict compositionality, and of a uniform combination of the components for best results.

If you've seen some, you've seen them all: Identifying variants of multiword expressions

no code implementations COLING 2018 Caroline Pasquer, Agata Savary, Carlos Ramisch, Jean-Yves Antoine

Multiword expressions, especially verbal ones (VMWEs), show idiosyncratic variability, which is challenging for NLP applications, hence the need for VMWE identification.

General Classification

VarIDE at PARSEME Shared Task 2018: Are Variants Really as Alike as Two Peas in a Pod?

no code implementations COLING 2018 Caroline Pasquer, Carlos Ramisch, Agata Savary, Jean-Yves Antoine

We describe the VarIDE system (standing for Variant IDEntification) which participated in the edition 1. 1 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs).

Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification

1 code implementation COLING 2018 Nicolas Zampieri, Manon Scholivet, Carlos Ramisch, Benoit Favre

This paper describes the Veyn system, submitted to the closed track of the PARSEME Shared Task 2018 on automatic identification of verbal multiword expressions (VMWEs).

Machine Translation TAG +1

Towards a Variability Measure for Multiword Expressions

no code implementations NAACL 2018 Caroline Pasquer, Agata Savary, Jean-Yves Antoine, Carlos Ramisch

One of the most outstanding properties of multiword expressions (MWEs), especially verbal ones (VMWEs), important both in theoretical models and applications, is their idiosyncratic variability.

Survey: Multiword Expression Processing: A Survey

no code implementations CL 2017 Mathieu Constant, G{\"u}l{\c{s}}en Eryi{\v{g}}it, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu

The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs.

Machine Translation

Annotation d'expressions polylexicales verbales en fran\ccais (Annotation of verbal multiword expressions in French)

no code implementations JEPTALNRECITAL 2017 C, Marie ito, Mathieu Constant, Carlos Ramisch, Agata Savary, Yannick Parmentier, Caroline Pasquer, Jean-Yves Antoine

Nous d{\'e}crivons la partie fran{\c{c}}aise des donn{\'e}es produites dans le cadre de la campagne multilingue PARSEME sur l{'}identification d{'}expressions polylexicales verbales (Savary et al., 2017).

Identification of Ambiguous Multiword Expressions Using Sequence Models and Lexical Resources

no code implementations WS 2017 Manon Scholivet, Carlos Ramisch

We present a simple and efficient tagger capable of identifying highly ambiguous multiword expressions (MWEs) in French texts.

mwetoolkit+sem: Integrating Word Embeddings in the mwetoolkit for Semantic MWE Processing

no code implementations LREC 2016 Silvio Cordeiro, Carlos Ramisch, Aline Villavicencio

This paper presents mwetoolkit+sem: an extension of the mwetoolkit that estimates semantic compositionality scores for multiword expressions (MWEs) based on word embeddings.

Word Embeddings

DeQue: A Lexicon of Complex Prepositions and Conjunctions in French

no code implementations LREC 2016 Carlos Ramisch, Alexis Nasr, Andr{\'e} Valli, Jos{\'e} Deulofeu

We introduce DeQue, a lexicon covering French complex prepositions (CPRE) like {``}{\`a} partir de{''} (from) and complex conjunctions (CCONJ) like {``}bien que{''} (although).

Comparing the Quality of Focused Crawlers and of the Translation Resources Obtained from them

no code implementations LREC 2014 Bruno Laranjeira, Viviane Moreira, Aline Villavicencio, Carlos Ramisch, Maria Jos{\'e} Finatto

Comparable corpora have been used as an alternative for parallel corpora as resources for computational tasks that involve domain-specific natural language processing.

Machine Translation Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.