Search Results for author:
Found 17 papers, 1 papers with code
Noisy Channel for Low Resource Grammatical Error Correction
This paper describes our contribution to the low-resource track of the BEA 2019 shared task on Grammatical Error Correction (GEC).
A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors
While rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit their training data.
Investigating NP-Chunking with Universal Dependencies for English
Chunking is a pre-processing task generally dedicated to improving constituency parsing.
Automatically Selecting the Best Dependency Annotation Design with Dynamic Oracles
This work introduces a new strategy to compare the numerous conventions that have been proposed over the years for expressing dependency structures and discover the one for which a parser will achieve the highest parsing performance.
Does syntax help discourse segmentation? Not so much
Discourse segmentation is the first step in building discourse parsers.
Cross-lingual and cross-domain discourse segmentation of entire documents
Discourse segmentation is a crucial step in building end-to-end discourse parsers.
Apprentissage d'analyseur en d\'ependances cross-lingue par projection partielle de d\'ependances (Cross-lingual learning of dependency parsers from partially projected dependencies )
Cet article pr{\'e}sente une m{\'e}thode simple de transfert cross-lingue de d{\'e}pendances.
CDGFr, un corpus en d\'ependances non-projectives pour le fran\ccais
Dans le cadre de l{'}analyse en d{\'e}pendances du fran{\c{c}}ais, le ph{\'e}nom{\`e}ne de la non-projectivit{\'e} est peu pris en compte, en majeure partie car les donne{\'e}s sur lesquelles sont entra{\^\i}n{\'e}s les analyseurs repr{\'e}sentent peu ou pas ces cas particuliers.
Validation Issues induced by an Automatic Pre-Annotation Mechanism in the Building of Non-projective Dependency Treebanks
In order to build large dependency treebanks using the CDG Lab, a grammar-based dependency treebank development tool, an annotator usually has to fill a selection form before parsing.
