Summary of the paper
| Title | REMOOV: A Tool for Online Handling of Out-of-Vocabulary Words in Machine Translation |
|---|---|
| Authors | Nizar Habash |
| Abstract | We present REMOOV, a tool for online handling of out-of-vocabulary (OOV) words in Statistical Machine Translation. REMOOV employs four techniques. Spelling expansion and morphological expansion are used to produce alternative in-vocabulary (INV) forms of OOV words. Dictionary term expansion and proper name transliteration produce target translations directly. These techniques can be used to expand the phrase table utilized in decoding or as part of an input/output lattice expansion. Results of using REMOOV show a consistent improvement over a state-of-the-art baseline. This paper describes the different components and parameters of the REMOOV tool. |
| Topics | Monolingual and multilingual LRs, Machine translation to or from Arabic, Machine translation, multilingual information retrieval, and cross-lingual information retrieval |
Full paper  |
REMOOV: A Tool for Online Handling of Out-of-Vocabulary Words in Machine Translation |
| Bibtex | @InProceedings{HABASH09.26, author = {Nizar Habash}, title = {REMOOV: A Tool for Online Handling of Out-of-Vocabulary Words in Machine Translation}, booktitle = {Proceedings of the Second International Conference on Arabic Language Resources and Tools}, year = {2009}, month = {April}, date = {22-23}, address = {Cairo, Egypt}, editor = {Khalid Choukri and Bente Maegaard}, publisher = {The MEDAR Consortium}, isbn = {2-9517408-5-9}, language = {english} } |