UNITRAN: A Principle-Based Approach to Machine Translation
Machine translation has been a particularly difficult problem in the area of Natural Language Processing for over two decades. Early approaches to translation failed since interaction effects of complex phenomena in part made translation appear to be unmanageable. Later approaches to the prob...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6963 |
| _version_ | 1826210868390526976 |
|---|---|
| author | Dorr, Bonnie Jean |
| author_facet | Dorr, Bonnie Jean |
| author_sort | Dorr, Bonnie Jean |
| collection | MIT |
| description | Machine translation has been a particularly difficult problem in the area of Natural Language Processing for over two decades. Early approaches to translation failed since interaction effects of complex phenomena in part made translation appear to be unmanageable. Later approaches to the problem have succeeded (although only bilingually), but are based on many language-specific rules of a context-free nature. This report presents an alternative approach to natural language translation that relies on principle-based descriptions of grammar rather than rule-oriented descriptions. The model that has been constructed is based on abstract principles as developed by Chomsky (1981) and several other researchers working within the "Government and Binding" (GB) framework. Thus, the grammar is viewed as a modular system of principles rather than a large set of ad hoc language-specific rules. |
| first_indexed | 2024-09-23T14:57:02Z |
| id | mit-1721.1/6963 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:57:02Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/69632019-04-10T14:26:04Z UNITRAN: A Principle-Based Approach to Machine Translation Dorr, Bonnie Jean Machine translation has been a particularly difficult problem in the area of Natural Language Processing for over two decades. Early approaches to translation failed since interaction effects of complex phenomena in part made translation appear to be unmanageable. Later approaches to the problem have succeeded (although only bilingually), but are based on many language-specific rules of a context-free nature. This report presents an alternative approach to natural language translation that relies on principle-based descriptions of grammar rather than rule-oriented descriptions. The model that has been constructed is based on abstract principles as developed by Chomsky (1981) and several other researchers working within the "Government and Binding" (GB) framework. Thus, the grammar is viewed as a modular system of principles rather than a large set of ad hoc language-specific rules. 2004-10-20T20:10:58Z 2004-10-20T20:10:58Z 1987-12-01 AITR-1000 http://hdl.handle.net/1721.1/6963 en_US AITR-1000 40098641 bytes 32491738 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Dorr, Bonnie Jean UNITRAN: A Principle-Based Approach to Machine Translation |
| title | UNITRAN: A Principle-Based Approach to Machine Translation |
| title_full | UNITRAN: A Principle-Based Approach to Machine Translation |
| title_fullStr | UNITRAN: A Principle-Based Approach to Machine Translation |
| title_full_unstemmed | UNITRAN: A Principle-Based Approach to Machine Translation |
| title_short | UNITRAN: A Principle-Based Approach to Machine Translation |
| title_sort | unitran a principle based approach to machine translation |
| url | http://hdl.handle.net/1721.1/6963 |
| work_keys_str_mv | AT dorrbonniejean unitranaprinciplebasedapproachtomachinetranslation |