Computing consensus translation from multiple machine translation systems

Bangalore, B.; Bordel, Germán; Riccardi, Giuseppe

doi:10.1109/asru.2001.1034659

Cited by 71 publications

(72 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the original use of MSA is the alignment of biological sequences, MSA algorithms can align sequences of symbols of any kind. Within the frame work of Natural Language Processing (NLP), MSA has been mainly used in automatic translation tasks [12,13]. All these approaches -including the one presented in this papercoincide in the creation of a graph of words from the result of the MSA.…”

Section: Graph Of Words Generationmentioning

confidence: 99%

A Multilingual SLU System Based on Semantic Decoding of Graphs of Words

Calvo

Hurtado

García

et al. 2012

Advances in Speech and Language Technologies for Iberian Languages

View full text Add to dashboard Cite

Calvo Lance, M.; Hurtado Oliver, LF.; García Granada, F.; Sanchís Arnal, E. (2012) Abstract. In this paper, we present a statistical approach to Language Understanding that allows to avoid the effort of obtaining new semantic models when changing the language. This way, it is not necessary to acquire and label new training corpora in the new language. Our approach consists of learning all the semantic models in a target language and to do the semantic decoding of the sentences pronounced in the source language after a translation process. In order to deal with the errors and the lack of coverage of the translations, a mechanism to generalize the result of several translators is proposed. The graph of words generated in this phase is the input to the semantic decoding algorithm specifically designed to combine statistical models and graphs of words. Some experiments that show the good behavior of the proposed approach are also presented.

show abstract

Section: Graph Of Words Generationmentioning

confidence: 99%

A Multilingual SLU System Based on Semantic Decoding of Graphs of Words

Calvo

Hurtado

García

et al. 2012

Advances in Speech and Language Technologies for Iberian Languages

View full text Add to dashboard Cite

show abstract

“…2 Now we explain how to formulate an algorithm. As is explained in the latter half of Section 2, a confusion network-based system combination approach takes three steps 3 as follows.…”

Section: Our Algorithmmentioning

confidence: 99%

“…The confusion network-based approach [2,16,6] enables us to combine several fragments from different MT outputs. In the first step, we select the sentencebased best single system via a MBR decoder (or single system outputs are often used as the backbone of the confusion network).…”

Section: Introductionmentioning

confidence: 99%

Minimum Bayes Risk Decoding with Enlarged Hypothesis Space in System Combination

Okita

Genabith

2012

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. This paper describes a new system combination strategy in Statistical Machine Translation. Tromble et al. (2008) introduced the evidence space into Minimum Bayes Risk decoding in order to quantify the relative performance within lattice or n-best output with regard to the 1-best output. In contrast, our approach is to enlarge the hypothesis space in order to incorporate the combinatorial nature of MBR decoding. In this setting, we perform experiments on three language pairs ES-EN, FR-EN and JP-EN. For ES-EN JRC-Acquis our approach shows 0.50 BLEU points absolute and 1.9% relative improvement obver the standard confusion network-based system combination without hypothesis expansion, and 2.16 BLEU points absolute and 9.2% relative improvement compared to the single best system. For JP-EN NTCIR-8 the improvement is 0.94 points absolute and 3.4% relative, and for FR-EN WMT09 0.30 points absolute and 1.3% relative compared to the single best system, respectively.

show abstract

“…Our algorithm for building this weighted graph of words works in two steps. First, the different recognition alternatives are aligned using a Multiple Sequence Alignment (MSA) algorithm [1]. To carry out this process, we have modified the ClustalW [9] Multiple Sequence Alignment software.…”

Section: A Grammatical Inference Algorithm To Build Graphs Of Wordsmentioning

confidence: 99%

Combining Several ASR Outputs in a Graph-Based SLU System

Calvo

Hurtado

García

et al. 2015

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. In this paper, we present an approach to Spoken Language Understanding (SLU) where we perform a combination of multiple hypotheses from several Automatic Speech Recognizers (ASRs) in order to reduce the impact of recognition errors in the SLU module. This combination is performed using a Grammatical Inference algorithm that provides a generalization of the input sentences by means of a weighted graph of words. We have also developed a specific SLU algorithm that is able to process these graphs of words according to a stochastic semantic modelling. The results show that the combinations of several hypotheses from the ASR module outperform the results obtained by taking just the 1-best transcription.

show abstract

Computing consensus translation from multiple machine translation systems

Cited by 71 publications

References 5 publications

A Multilingual SLU System Based on Semantic Decoding of Graphs of Words

A Multilingual SLU System Based on Semantic Decoding of Graphs of Words

Minimum Bayes Risk Decoding with Enlarged Hypothesis Space in System Combination

Combining Several ASR Outputs in a Graph-Based SLU System

Contact Info

Product

Resources

About