Abstract / Description of output
In this paper we explore the novel idea of building a single universal reordering model from English to a large number of target languages. To build this model we exploit typological features of word order for a large number of target languages together with source (English) syntactic features and we train this model on a single combined parallel corpus representing all (22) involved language pairs. We contribute experimental evidence for the usefulness of linguistically defined typological features for building such a model. When the universal reordering model is used for preordering followed by monotone translation (no reordering inside the decoder), our experiments show that this pipeline gives comparable or improved translation performance with a phrase-based baseline for a large number of language pairs (12 out of 22) from diverse language families.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers |
| Place of Publication | Osaka, Japan |
| Publisher | The COLING 2016 Organizing Committee |
| Pages | 3167-3176 |
| Number of pages | 10 |
| Publication status | Published - 30 Nov 2016 |
| Event | 26th International Conference on Computational Linguistics - Osaka, Japan Duration: 11 Dec 2016 → 16 Dec 2016 http://coling2016.anlp.jp/ |
Conference
| Conference | 26th International Conference on Computational Linguistics |
|---|---|
| Abbreviated title | COLING 2016 |
| Country/Territory | Japan |
| City | Osaka |
| Period | 11/12/16 → 16/12/16 |
| Internet address |