Using Sense-labeled Discourse Connectives for Statistical Machine Translation
| Type of publication: | Conference paper |
| Citation: | Meyer_EACL2012-HYTRA_2012 |
| Publication status: | Published |
| Booktitle: | Proceedings of the EACL2012 Workshop on Hybrid Approaches to Machine Translation (HyTra) |
| Year: | 2012 |
| Month: | April |
| Pages: | 129--138 |
| Location: | Avignon, FR |
| Abstract: | This article shows how the automatic disambiguation of discourse connectives can improve Statistical Machine Translation (SMT) from English to French. Connectives are firstly disambiguated in terms of the discourse relation they signal between segments. Several classifiers trained using syntactic and semantic features reach state-of-the-art performance, with F1 scores of 0.6 to 0.8 over thirteen ambiguous English connectives. Labeled connectives are then used into SMT systems either by modifying their phrase table, or by training them on labeled corpora. The best modified SMT systems improve the translation of connectives without degrading BLEU scores. A threshold-based SMT system using only high-confidence labels improves BLEU scores by 0.2–0.4 points. |
| Keywords: | Automated Disambiguation, discourse connectives, Statistical Machine Translation |
| Projects |
Idiap COMTIS |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
