Title | ||
---|---|---|
Recursive neural network based word topology model for hierarchical phrase-based speech translation |
Abstract | ||
---|---|---|
Recursive word topology structure is commonly found in natural language sentences, and discovering this structure can help us to not only identify the units that a sentence contains but also how they interact to form a whole. In this paper, we explore a novel recursive neural network (RNN) based word topology model (WordTM) for hierarchical phrase-based (HPB) speech translation, which captures the topological structure of the words on the source side in a syntactically and semantically meaningful order. Experiments show that our WordTM significantly outperforms the state-of-the-art soft syntactic constraints. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICASSP.2014.6855133 | ICASSP |
Keywords | Field | DocType |
speech processing,rnn,soft syntactic constraints,recursive neural network,wordtm,hpb speech translation,word topology model,language translation,topological structure,hierarchical phrase-based speech translation,natural language sentences,natural language processing,neural nets,recursive neural network based word topology model,speech,network topology,topology,merging,semantics,neural networks | Computer science,Syntactic constraints,Recurrent neural network,Phrase,Artificial intelligence,Natural language processing,Recursion,Topology,Word error rate,Speech recognition,Natural language,Speech translation,Sentence | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.36 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shixiang Lu | 1 | 19 | 3.39 |
Wei Wei | 2 | 22 | 20.02 |
Xiaoyin Fu | 3 | 10 | 2.53 |
Bo Xu | 4 | 241 | 36.59 |