Name
Abstract | ||
|---|---|---|
Hierarchical phrase-based machine translation [1] (Hiero) is a prominent approach for Statistical Machine Translation usually comparable to or better than conventional phrase-based systems. But Hiero typically uses the CKY decoding algorithm which requires the entire input sentence before decoding begins, as it produces the translation in a bottom-up fashion. Left-to-right (LR) decoding [2] is a promising decoding algorithm for Hiero that produces the output translation in left to right order. In this paper we focus on simultaneous translation using the Hiero translation framework. In simultaneous translation, translations are generated incrementally as source language speech input is processed. We propose a novel approach for incremental translation by integrating segmentation and decoding in LR-Hiero. We compare two incremental decoding algorithms for LR-Hiero and present translation quality scores (BLEU) and the latency of generating translations for both decoders on audio lectures from the TED collection. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/SLT.2014.7078552 | Spoken Language Technology Workshop |
Keywords | Field | DocType |
language translation,natural language processing,speech coding,statistical analysis,BLEU,CKY decoding algorithm,Hiero translation framework,LR decoding,LR-Hiero,TED collection,audio lectures,hierarchical phrase-based machine translation system,incremental decoding algorithm,incremental translation,left-to-right decoding,segmentation,source language speech input,statistical machine translation,translation quality scores,Hierarchical Phrase-based Translation (Hiero),Incremental Decoding,Left-to-Right Decoding,Statistical Machine Translation (SMT) | Rule-based machine translation,Example-based machine translation,Computer science,Machine translation,Phrase,Synchronous context-free grammar,Natural language processing,Artificial intelligence,Pattern recognition,Segmentation,Speech recognition,Decoding methods,Sentence | Conference |
ISSN | Citations | PageRank |
2639-5479 | 0 | 0.34 |
References | Authors | |
16 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Maryam Siahbani | 1 | 29 | 4.53 |
| Ramtin Mehdizadeh Seraj | 2 | 0 | 0.34 |
| Baskaran Sankaran | 3 | 155 | 13.65 |
| Anoop Sarkar | 4 | 1017 | 88.82 |