Abstract | ||
---|---|---|
This paper proposes Naxi-Chinese bilingual word alignment method based on entity constraint for the characteristic that entity and entity is alignment in bilingual alignment. First, we mark the corpus of Naxi word segmentation and entity label, using Conditional Random Fields constructs the model of Naxi word segmentation and entity recognition to achieve Naxi word segmentation and entity recognition. Then, using entity alignment constraint relation of Naxi-Chinese sentence uses the specific marker to mark out bilingual entity of Naxi-Chinese sentence. Finally, we introduce features, such as fertility probabilities and distortion probabilities et al, and achieve the Naxi-Chinese bilingual alignment model by GIZA++. Naxi-Chinese bilingual word alignment experimental result shows the method proposed by this paper has better effect compared to only use IBM Models. © 2013 Springer-Verlag. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-45185-0_40 | CLSW |
Keywords | Field | DocType |
conditional random fields,distortion probabilities,entity alignment constraint,fertility probabilities | Conditional random field,IBM,Computer science,Text segmentation,Natural language processing,Artificial intelligence,Distortion,Sentence,Naxi | Conference |
Volume | Issue | ISSN |
8229 LNAI | null | 16113349 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiuzhen Yang | 1 | 0 | 0.34 |
Zhengtao Yu | 2 | 460 | 69.08 |
Jianyi Guo | 3 | 20 | 10.99 |
Xiao Pan | 4 | 12 | 8.24 |
Cunli Mao | 5 | 51 | 11.54 |