Proceedings chapter
OA Policy
English

Combining pre-editing and post-editing to improve SMT of user-generated content

Presented at

Nice (France), 2 Sept. 2013

Published in

O'Brien, S., Simard, M. & Specia, L. (Ed.), Proceedings of MT Summit XIV Workshop on Post-editing Technology and Practice, p. 45-53

Publication date

2013

Abstract

The poor quality of user-generated content (UGC) found in forums hinders both readability and machine-translatability. To improve these two aspects, we have developed human- and machine-oriented pre-editing rules, which correct or reformulate this content. In this paper we pre-sent the results of a study which investigates whether pre-editing rules that improve the quality of statistical machine translation (SMT) output also have a positive impact on post-editing productivity. For this study, pre-editing rules were applied to a set of French sentences extracted from a technical forum. After SMT, the post-editing temporal effort and final quality are compared for translations of the raw source and its pre-edited version. Results obtained suggest that pre-editing speeds up post-editing and that the combination of the two processes is worthy of further investigation.

Keywords

  • User-generated content
  • Pre-editing
  • Post-editing
  • Statistical machine translation

UNIGE research groups

Citation (ISO format)

GERLACH, Johanna et al. Combining pre-editing and post-editing to improve SMT of user-generated content. In: Proceedings of MT Summit XIV Workshop on Post-editing Technology and Practice. O’Brien, S., Simard, M. & Specia, L. (Ed.). Nice (France). [s.l.] : [s.n.], 2013. p. 45–53.

Main files (1)

Proceedings chapter (Accepted version)

Identifiers

  • PID : unige:30952
3079views
1684downloads

Technical informations

Creation

05/11/2013 12:21:00

First validation

05/11/2013 12:21:00

Update

14/03/2023 20:36:02

Status update

14/03/2023 20:36:02

Last indexation

25/09/2025 22:06:23
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated