Abstract | ||
---|---|---|
This paper describes a novel technique for incorporating syntactic knowledge into phrase-based machine translation through incremental syntactic parsing. Bottom-up and top-down parsers typically require a completed string as input. This requirement makes it difficult to incorporate them into phrase-based translation, which generates partial hypothesized translations from left-to-right. Incremental syntactic language models score sentences in a similar left-to-right fashion, and are therefore a good mechanism for incorporating syntax into phrase-based translation. We give a formal definition of one such lineartime syntactic language model, detail its relation to phrase-based decoding, and integrate the model with the Moses phrase-based translation system. We present empirical results on a constrained Urdu-English translation task that demonstrate a significant BLEU score improvement and a large decrease in perplexity. |
Year | Venue | Keywords |
---|---|---|
2011 | ACL | incremental syntactic language model,phrase-based decoding,significant bleu score improvement,incremental syntactic parsing,syntactic knowledge,phrase-based translation,lineartime syntactic language model,urdu-english translation task,moses phrase-based translation system,phrase-based machine translation,markov processes,english language,parsers,context free grammars,decoding,graphs,language model,statistical analysis,machine translation,syntax,hierarchies |
Field | DocType | Volume |
Noun phrase,Rule-based machine translation,Computer science,Machine translation,Phrase,Synchronous context-free grammar,Speech recognition,Phrase structure rules,Natural language processing,Artificial intelligence,Transfer-based machine translation,Computer-assisted translation | Conference | aclanthology.org |
Citations | PageRank | References |
13 | 0.62 | 50 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lane Schwartz | 1 | 209 | 18.01 |
Chris Callison-Burch | 2 | 4872 | 259.75 |
William Schuler | 3 | 125 | 17.78 |
Stephen Wu | 4 | 147 | 11.73 |