Unification-Based Glossing
Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence. Natural Language. Pages 1382-1388.
Abstract
We present an approach to syntax-based machine translation that combines unification-style interpretation with statistical processing. This approach enables us to translat e any Japan ese newspaper article into English, with quality far better than a word-for-word translation. Novel ideas include the use of feature structures to encode word lattic es and the use of unifi cati on to co mpos e and manipulat e lattices . Unification also allows us to specify abstract features that delay target-language synthesis until enough source-language information is assembled. Our statistical component enables us to search efficiently among competing translations and locate those with high English flu ency.
@inproceedings{ijcai1995p178,
title = {Unification-Based Glossing},
author = {Hatzivassiloglou, Vasileios and Knight, Kevin},
booktitle = {Proceedings of the Fourteenth International Joint Conference on
Artificial Intelligence, {IJCAI-95}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Chris S. Mellish},
pages = {1382--1388},
year = {1995},
note = {Natural Language},
url = {https://ijcai.org/proceedings/1995/178},
}
TY - CPAPER TI - Unification-Based Glossing AU - Hatzivassiloglou, Vasileios AU - Knight, Kevin T2 - Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, IJCAI-95 PB - International Joint Conferences on Artificial Intelligence PY - 1995 SP - 1382 EP - 1388 UR - https://ijcai.org/proceedings/1995/178 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
