Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities
Ngoc Quang Luong, Andrei Popescu-Belis, Annette Rios Gonzales, Don Tuggener
Abstract
We implement a fully probabilistic model to combine the hypotheses of a Spanish anaphora resolution system with those of a Spanish-English machine translation system. The probabilities over antecedents are converted into probabilities for the features of translated pronouns, and are integrated with phrase-based MT using an additional translation model for pronouns. The system improves the translation of several Spanish personal and possessive pronouns into English, by solving translation divergencies such as ‘ella’ vs. ‘she’/‘it’ or ‘su’ vs. ‘his’/‘her’/‘its’/‘their’. On a test set with 2,286 pronouns, a baseline system correctly translates 1,055 of them, while ours improves this by 41. Moreover, with oracle antecedents, possessives are translated with an accuracy of 83%.- Anthology ID:
- E17-2100
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 631–636
- Language:
- URL:
- https://aclanthology.org/E17-2100
- DOI:
- Cite (ACL):
- Ngoc Quang Luong, Andrei Popescu-Belis, Annette Rios Gonzales, and Don Tuggener. 2017. Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 631–636, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities (Luong et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/E17-2100.pdf
- Code
- a-rios/CorefMT