Hebrew and Arabic are related but mutually incomprehensible languages with complex morphology and scarce parallel corpora. Machine translation between the two languages is therefore interesting and challenging. We discuss similarities and differences between Hebrew and Arabic, the benefits and challenges that they induce, respectively, and their implications on machine translation. We highlight the shortcomings of using English as a pivot language and advocate a direct, transfer-based and linguistically-informed (but still statistical, and hence scalable) approach. We report preliminary results of the two systems we are currently developing, for translation in both directions.
Bibliographical noteFunding Information:
Acknowledgements We are grateful to Gennadi Lembersky for his help. Reshef Shilon and Shuly Wint-ner were partly supported by The Israel Science Foundation (grant No. 137/06). Alon Lavie’s work was supported in part by NSF grants IIS-0534217 and IIS-0915327. All of Nizar Habash’s contributions were funded by Columbia University’s Center for Computational Learning Systems (CCLS).
- Transfer-based MT
ASJC Scopus subject areas
- Language and Linguistics
- Linguistics and Language
- Artificial Intelligence