Results 1  10
of
19
Greedy Decoding for Statistical Machine Translation in Almost Linear Time
, 2003
"... We present improvements to a greedy decoding algorithm for statistical machine translation that reduce its time complexity from at least cubic (O(n^6) when applied navely) to practically linear time without sacrificing translation quality. We achieve this by integrating hypothesis evaluati ..."
Abstract

Cited by 33 (2 self)
 Add to MetaCart
(Show Context)
We present improvements to a greedy decoding algorithm for statistical machine translation that reduce its time complexity from at least cubic (O(n^6) when applied navely) to practically linear time without sacrificing translation quality. We achieve this by integrating hypothesis evaluation into hypothesis creation, tiling improvements over the translation hypothesis at the end of each search iteration, and by imposing restrictions on the amount of word reordering during decoding.
An ngrambased statistical machine translation decoder
 PROC. OF THE 9TH EUROPEAN CONFERENCE ON SPEECH COMMUNICATION AND TECHNOLOGY, INTERSPEECH’05
, 2005
"... In this paper we describe MARIE, an Ngrambased statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. ..."
Abstract

Cited by 25 (15 self)
 Add to MetaCart
(Show Context)
In this paper we describe MARIE, an Ngrambased statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. The search graph structure is designed to perform very accurate comparisons, what allows for a high level of pruning, improving the decoder efficiency. We report several techniques for efficiently prune out the search space. The combinatory explosion of the search space derived from the search graph structure is reduced by limiting the number of reorderings a given translation is allowed to perform, and also the maximum distance a word (or a phrase) is allowed to be reordered. We finally report translation accuracy results on three different translation tasks.
Chunkbased statistical translation
 In Proceedings of the Conference of the Association for Computational Linguistics
, 2003
"... This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first performs chunking. Then, each word in a chunk is translated. Finally, translated chunks are reordered. Under this scenario of ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
(Show Context)
This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first performs chunking. Then, each word in a chunk is translated. Finally, translated chunks are reordered. Under this scenario of translation modeling, we have experimented on a broadcoverage JapaneseEnglish traveling corpus and achieved improved performance. 1
Examplebased decoding for statistical machine translation
 in Proc. of MT Summit IX
, 2003
"... This paper presents a decoder for statistical machine translation that can take advantage of the examplebased machine translation framework. The decoder presented here is based on the greedy approach to the decoding problem, but the search is initiated from a similar translation extracted from a bi ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
This paper presents a decoder for statistical machine translation that can take advantage of the examplebased machine translation framework. The decoder presented here is based on the greedy approach to the decoding problem, but the search is initiated from a similar translation extracted from a bilingual corpus. The experiments on multilingual translations showed that the proposed method was far superior to a wordbyword generation beam search algorithm. 1
Bidirectional Decoding for Statistical Machine Translation
 IN PROC. OF COLING 2002
, 2002
"... This paper describes the righttoleft decoding method, which translates an input string by generating in righttoleft direction. In addition, presented is the bidirectional decoding method, that can take both of the advantages of lefttoright and righttoleft decoding method by generating output ..."
Abstract

Cited by 7 (1 self)
 Add to MetaCart
(Show Context)
This paper describes the righttoleft decoding method, which translates an input string by generating in righttoleft direction. In addition, presented is the bidirectional decoding method, that can take both of the advantages of lefttoright and righttoleft decoding method by generating output in both ways and by merging hypothesized partial outputs of two directions. The experimental results on Japanese and English translation showed that the righttoleft was better for EnglithtoJapanese translation, while the lefttoright was suitable for JapanesetoEnglish translation. It was also observed that the bidirectional method was better for EnglishtoJapanese translation.
Automatic transcription of Lithuanian text using dictionary
 Informatica
, 2006
"... Abstract. There is presented a technique of transcribing Lithuanian text into phonemes for speech recognition. Textphoneme transformation has been made by formal rules and the dictionary. Formal rules were designed to set the relationship between segments of the text and units of formalized speech ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
Abstract. There is presented a technique of transcribing Lithuanian text into phonemes for speech recognition. Textphoneme transformation has been made by formal rules and the dictionary. Formal rules were designed to set the relationship between segments of the text and units of formalized speech sounds – phonemes, dictionary – to correct transcription and specify stress mark and position. Proposed the automatic transcription technique was tested by comparing its results with manually obtained ones. The experiment has shown that less than 6 % of transcribed words have not matched. Key words: speech recognition, grapheme to phoneme transcription. 1.
Refined Lexicon Models for Statistical Machine Translation using a Maximum Entropy Approach
 In Proc. of ACLEACL
, 2001
"... Typically, the lexicon models used in statistical machine translation systems do not include any kind of linguistic or contextual information, which often leads to problems in performing a correct wordsense disambiguation. One way to deal with this problem within the statistical framework is ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
Typically, the lexicon models used in statistical machine translation systems do not include any kind of linguistic or contextual information, which often leads to problems in performing a correct wordsense disambiguation. One way to deal with this problem within the statistical framework is using maximum entropy methods. In this paper, we present how to use this information within a statistical machine translation system. We show that it is possible to significantly decrease training and test corpus perplexity of the translation models. In addition, we perform a rescoring of NBest lists using our maximum entropy model and thereby yield an improvement in translation quality. Experimental results are presented with the so called "Vermobil Task".
STATISTICAL MACHINE TRANSLATION DECODER BASED ON PHRASE
"... This paper describes a decoding algorithm for statistical machine translation based on phrases. In the past, the solution to the decoding problem were inspired from that of speech recognizers, translating each input word into one or more output words generating in lefttoright direction. The algori ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
This paper describes a decoding algorithm for statistical machine translation based on phrases. In the past, the solution to the decoding problem were inspired from that of speech recognizers, translating each input word into one or more output words generating in lefttoright direction. The algorithm presented here iteratively constructs phrases or chunks of cepts until all the input words are consumed. This behavior resulted in computational complexity higher than those with lefttoright constraints, though the translation accuracy is better from the JapanesetoEnglish translation experiments. 1.
Statistical Machine Translation on Paraphrased Corpora
"... This paper presents a statistical machine translation trained on normalized corpora. The automatic paraphrasing is carried out by inducing paraphrasing expressions from a bilingual corpus. Then, the normalization is treated as a specific paraphrase of a given input determined by the frequency in a c ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This paper presents a statistical machine translation trained on normalized corpora. The automatic paraphrasing is carried out by inducing paraphrasing expressions from a bilingual corpus. Then, the normalization is treated as a specific paraphrase of a given input determined by the frequency in a corpus. The experimental results on JapanesetoEnglish translation with normalized English corpus exhibited the reduction of worderrorrate by 8 % and the improvement of subjective evaluation from 70 % into 72.5%. 1.
Computational Complexity of Statistical Machine Translation
"... In this paper we study a set of problems that are of considerable importance to Statistical Machine Translation (SMT) but which have not been addressed satisfactorily by the SMT research community. Over the last decade, a variety of SMT algorithms have been built and empirically tested whereas littl ..."
Abstract
 Add to MetaCart
In this paper we study a set of problems that are of considerable importance to Statistical Machine Translation (SMT) but which have not been addressed satisfactorily by the SMT research community. Over the last decade, a variety of SMT algorithms have been built and empirically tested whereas little is known about the computational complexity of some of the fundamental problems of SMT. Our work aims at providing useful insights into the the computational complexity of those problems. We prove that while IBM Models 12 are conceptually and computationally simple, computations involving the higher (and more useful) models are hard. Since it is unlikely that there exists a polynomial time solution for any of these hard problems (unless P = NP and P #P = P), our results highlight and justify the need for developing polynomial time approximations for these computations. We also discuss some practical ways of dealing with complexity. 1