Title | ||
---|---|---|
Normalizing German and English Inflectional Morphology to Improve Statistical Word Alignment |
Abstract | ||
---|---|---|
German has a richer system of inflectional morphology than English, which causes problems for current approaches to statistical word alignment. Using Giza++ as a reference implementation of the IBM Model 1, an HMM-based alignment and IBM Model 4, we measure the impact of normalizing inflectional morphology on German-English statistical word alignment. We demonstrate that normalizing inflectional morphology improves the perplexity of models and reduces alignment errors. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30194-3_6 | Lecture Notes in Computer Science |
Field | DocType | Volume |
Noun phrase,Perplexity,IBM,Markov model,Computer science,Machine translation,Model-based reasoning,Speech recognition,Artificial intelligence,Natural language processing,Hidden Markov model,German | Conference | 3265 |
ISSN | Citations | PageRank |
0302-9743 | 15 | 1.01 |
References | Authors | |
13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon Corston-Oliver | 1 | 349 | 25.25 |
Michael Gamon | 2 | 1484 | 89.50 |