Search Results for author:
Found 18 papers, 3 papers with code
Improving Precision of Grammatical Error Correction with a Cheat Sheet
In this paper, we explore two approaches of generating error-focused phrases and examine whether these phrases can lead to better performance in grammatical error correction for the restricted track of BEA 2019 Shared Task on GEC.
Artificial Error Generation with Fluency Filtering
The quantity and quality of training data plays a crucial role in grammatical error correction (GEC).
A New Annotation Scheme for the Sejong Part-of-speech Tagged Corpus
In this paper we present a new annotation scheme for the Sejong part-of-speech tagged corpus based on Universal Dependencies style annotation.
Le benchmarking de la reconnaissance d'entit\'es nomm\'ees pour le fran\ccais (Benchmarking for French NER)
Cet article pr{\'e}sente une t{\^a}che du benchmarking de la reconnaissance de l{'}entit{\'e} nomm{\'e}e (REN) pour le fran{\c{c}}ais.
Une note sur l'analyse du constituant pour le fran\ccais (A Note on constituent parsing for French)
Cet article traite des analyses d{'}erreurs quantitatives et qualitatives sur les r{\'e}sultats de l{'}analyse syntaxique des constituants pour le fran{\c{c}}ais.
L'optimisation du plongement de mots pour le fran\ccais : une application de la classification des phrases (Optimization of Word Embeddings for French : an Application of Sentence Classification)
Nous proposons trois nouvelles m{\'e}thodes pour construire et optimiser des plongements de mots pour le fran{\c{c}}ais.
Building a Better Bitext for Structurally Different Languages through Self-training
We propose a novel method to bootstrap the construction of parallel corpora for new pairs of structurally different languages.
Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies
This paper describes UALing{'}s approach to the \textit{CoNLL 2017 UD Shared Task} using corpus selection techniques to reduce training data size.
Second-Order Belief Hidden Markov Models
The probabilistic HMMs have been one of the most used techniques based on the Bayesian model.
Named Entity Corpus Construction using Wikipedia and DBpedia Ontology
In this paper, we propose a novel method to automatically build a named entity corpus based on the DBpedia ontology.
Using the International Standard Language Resource Number: Practical and Technical Aspects
This paper describes the International Standard Language Resource Number (ISLRN), a new identification schema for Language Resources where a Language Resource is provided with a unique and universal name using a standardized nomenclature.
