Decoding algorithm in statistical machine translation

Wang, Ye-Yi; Waibel, Alex

doi:10.3115/976909.979664

Cited by 64 publications

(51 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, hypotheses with different C can be stored in the same list. In order to properly compare the hypothesis that covers different parts of the source sentence, estimation (usually heuristic) of the contribution to the score of the parts, that are not yet covered, can be introduced [50]. Third, in order to reduce the computational cost of the algorithm, re-ordering restrictions must be introduced.…”

Section: Non-monotone Searchmentioning

confidence: 99%

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Cánovas

Tomás

Lloret

et al. 2013

Computer Standards & Interfaces

View full text Add to dashboard Cite

Abstract-Synergic combination of different sources of knowledge is a key issue for the development of modern statistical translators. Reconnaissance, and thus the translation, can be improved by adding new heuristic characteristics. In this work, a speech translation statistical system that adds additional other-than-voice information in a voice translation system is presented. The additional information serves as a base for the loglinear combination of several statistical models. We obtain the characteristics vectors using a statistical model that is based on the N-best reconnaissance list. We describe the theoretical framework of the problem, summarize the overall architecture of the system, and show how the system is enhanced with the additional information. Our real prototype implements a real-time speech translation system from Spanish to English that is adapted to specific teaching-related environments. Finally, we will provide and explain the system performance results. A tool like the one presented in this article may increase the participation rate of the foreign students to the lecture classes and talks.

show abstract

Section: Non-monotone Searchmentioning

confidence: 99%

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Cánovas

Tomás

Lloret

et al. 2013

Computer Standards & Interfaces

View full text Add to dashboard Cite

show abstract

“…With the exception of the greedy algorithm [4], the rest of them use the concept of partial translation hypothesis to perform the search [1][8] [12]. In a partial translation hypothesis, some of the source words have been used to generate a target prefix.…”

Section: Decoding Algorithmsmentioning

confidence: 99%

Statistical Machine Translation Decoding Using Target Word Reordering

Tomás

Casacuberta

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the field of pattern recognition, the design of an efficient decoding algorithm is critical for statistical machine translation. The most common statistical machine translation decoding algorithms use the concept of partial hypothesis. Typically, a partial hypothesis is composed by a subset of source positions, which indicates the words that have been translated in this hypothesis, and a prefix of the target sentence. Thus, the target sentence is generated from left to right obtaining source words in an arbitrary order. We present a new approach, where the source sentence is translated from left to right and the possible word reordering is performed at the target prefix. We implemented this approach using a multi-stack decoding technique for a phrase-based model, and compared it with both a conventional approach and a monotone approach. Our experiments show how the new approach can significantly reduce the search time without increasing the search errors.

show abstract

“…c.Expand the 'max' cell to the largest possible rectangle regions (R start , R end , C start ,C end ) under two constraints: (1). all the cells in the expanded region accord with the evaluation function ; (2). all the cells should not be marked.…”

Section: -1 Extracting Directly Through Ibm Word-based Modelmentioning

confidence: 99%

“…We use the HMM-based alignment model introduced in [8]. For a source phrase that ranges from position 1 j to 2 j in sentence, we can get the corresponding target phrase's beginning position and ending position to extract the phrase translation. Just like the method described in 2-1, a given factor that prevents the length of the phrase pairs differ greatly is needed.…”

Section: -3 Extracting Phrase Pairs From Hmm Word Alignment Modelmentioning

confidence: 99%

See 1 more Smart Citation

The CASIA Phrase-Based Machine Translation System

Yang¹,

Chen²,

Pang³

et al.

2005 International Conference on Natural Language Processing and Knowledge Engineering

View full text Add to dashboard Cite

In this paper we propose a phrase-based translation system. In the system, we use phrase translation model instead of word-based model. An improved method of computing phrase translation probability is studied. We translate numeral phrases first by using a standard templates depository. We develop a phrase-based decoder that employs a beam search algorithm. To make the result more reasonable, we apply those words with fertility probability of zero. We improve the previously proposed tracing back algorithm to get the best path. Some experiments concerned are presented.

show abstract

Decoding algorithm in statistical machine translation

Cited by 64 publications

References 3 publications

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Statistical speech translation system based on voice recognition optimization using multimodal sources of knowledge and characteristics vectors

Statistical Machine Translation Decoding Using Target Word Reordering

The CASIA Phrase-Based Machine Translation System

Contact Info

Product

Resources

About