1 |
Efficient Bilingual Generalization from Neural Transduction Grammar Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Efficient Bilingual Generalization from Neural Transduction Grammar Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Coerced Markov Models for Cross-Lingual Lexical-Tag Relations
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Coerced Markov Models For Cross-Lingual Lexical-Tag Relations
|
|
Fung, Pascale; Wu, Dekai. - : Proceedings of the Sixth International Conference on Theoretical and Methodological Issues in Machine Translation, 1995
|
|
Abstract:
We introduce the Coerced Markov Model (CMM) to model the relationship between the lexical sequence of a source language and the tag sequence of a target language, with the objective of constraining search in statistical transfer-based machine translation systems. CMMs differ from Hidden Markov Models in that state sequence assignments can take on values coerced from external sources. Given a Chinese sentence, a CMM can be used to predict the corresponding English tag sequence, thus constraining the English lexical sequence produced by a translation model. The CMM can also be used to score competing translation hypotheses in N-best models. Three fundamental problems for CMM designed are discussed. Their solutions lead to the training and testing stages of CMM.
|
|
Keyword:
Computer science; Information technology
|
|
URL: https://doi.org/10.7916/D86117MK
|
|
BASE
|
|
Hide details
|
|
15 |
Coerced Markov Models For Cross-Lingual Lexical-Tag Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Coerced Markov Models for Cross-Lingual Lexical-Tag Relations ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Aligning a Parallel English-Chinese Corpus Statistically with Lexical Criteria ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|