Weighted Set-Theoretic Alignment of Comparable Sentences

Tipo

Inproceedings

Fecha

2017-08-03

Autores

Andoni Azpeitia Zaldua, Thierry Etchegoyhen, Eva Martínez García

Libro

Proceedings of the 10th Workshop on Building and Using Comparable Corpora

@Inproceedings{
author ={Andoni Azpeitia Zaldua, Thierry Etchegoyhen, Eva Martínez García},
title ={Weighted Set-Theoretic Alignment of Comparable Sentences},
booktitle ={Proceedings of the 10th Workshop on Building and Using Comparable Corpora},
publisher ={Association for Computational Linguistics},
address ={Vancouver, Canada},
date ={2017-08-03},
year ={2017},
pages ={41-45},
keys ={

BUCC 2017, Comparable Corpora, Sentence Alignment

},
abstract ={

This article presents the STACCw system for the BUCC 2017 shared task on parallel sentence extraction from comparable corpora. The original STACC approach, based on set-theoretic operations over bags of words, had been previously shown to be efficient and portable across domains and alignment scenarios. We describe an extension of this approach with a new weighting scheme and show that it provides significant improvements on the datasets provided for the shared task.

},
ISBN ={978-1-5108-4575-6},
}