BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora

Francis Grégoire, Philippe Langlais


Abstract
This paper describes our participation in BUCC 2017 shared task: identifying parallel sentences in comparable corpora. Our goal is to leverage continuous vector representations and distributional semantics with a minimal use of external preprocessing and postprocessing tools. We report experiments that were conducted after transmitting our results.
Anthology ID:
W17-2509
Volume:
Proceedings of the 10th Workshop on Building and Using Comparable Corpora
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Serge Sharoff, Pierre Zweigenbaum, Reinhard Rapp
Venue:
BUCC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–50
Language:
URL:
https://aclanthology.org/W17-2509
DOI:
10.18653/v1/W17-2509
Bibkey:
Cite (ACL):
Francis Grégoire and Philippe Langlais. 2017. BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora. In Proceedings of the 10th Workshop on Building and Using Comparable Corpora, pages 46–50, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
BUCC 2017 Shared Task: a First Attempt Toward a Deep Learning Framework for Identifying Parallel Sentences in Comparable Corpora (Grégoire & Langlais, BUCC 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2509.pdf