Improved statistical alignment models

Och, Franz Josef; Ney, Hermann

doi:10.3115/1075218.1075274

Cited by 513 publications

(311 citation statements)

References 4 publications

Supporting

Mentioning

305

Contrasting

Unclassified

Order By: Relevance

“…In the first phase, words are aligned based on IBM model. The standard way of aligning word is the method implemented in GIZA++ [12,13]; In the next phase, Thrax grammar extractor is used to extract SCFGs with the aid of Hadoop method that is applicable to large datasets [14]. It also supports extraction of both Hiero [7] and SAMT grammars [15] with extraction heuristics.…”

Section: Proposed Methodsmentioning

confidence: 99%

A new model for persian multi-part words edition based on statistical machine translation

Zahedi

Arjomandzadeh

2016

JAIDM

View full text Add to dashboard Cite

Multi-part words in English language are hyphenated and hyphen is used to separate different parts. Persian language consists of multi-part words as well. Based on Persian morphology, half-space character is needed to separate parts of multi-part words where in many cases people incorrectly use space character instead of half-space character. This common incorrectly use of space leads to some serious issues in Persian text processing and text readability. In order to cope with the issues, this work proposes a new model to correct spacing in multi-part words. The proposed method is based on statistical machine translation paradigm. In machine translation paradigm, text in source language is translated into a text in destination language on the basis of statistical models whose parameters are derived from the analysis of bilingual text corpora. The proposed method uses statistical machine translation techniques considering unedited multi-part words as a source language and the space-edited multi-part words as a destination language. The results show that the proposed method can edit and improve spacing correction process of Persian multi-part words with a statistically significant accuracy rate.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

A new model for persian multi-part words edition based on statistical machine translation

Zahedi

Arjomandzadeh

2016

JAIDM

View full text Add to dashboard Cite

show abstract

“…Unlike most of the alignment models, where training is carried out with the EM (Expectation Maximisation) algorithm [20], our system allows using previous alignments that can be difficult to find. All the alignment hypotheses that can be obtained with different methods will serve as a reference for future alignment tasks.…”

Section: Linguistic Processingmentioning

confidence: 99%

Incorporating Linguistic Information to Statistical Word-Level Alignment

Cendejas

Barceló

Gelbukh

et al. 2009

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

View full text Add to dashboard Cite

Abstract. Parallel texts are enriched by alignment algorithms, thus establishing a relationship between the structures of the implied languages. Depending on the alignment level, the enrichment can be performed on paragraphs, sentences or words, of the expressed content in the source language and its translation. There are two main approaches to perform word-level alignment: statistical or linguistic. Due to the dissimilar grammar rules the languages have, the statistical algorithms usually give lower precision. That is why the development of this type of algorithms is generally aimed at a specific language pair using linguistic techniques. A hybrid alignment system based on the combination of the two traditional approaches is presented in this paper. It provides user-friendly configuration and is adaptable to the computational environment. The system uses linguistic resources and procedures such as identification of cognates, morphological information, syntactic trees, dictionaries, and semantic domains. We show that the system outperforms existing algorithms.

show abstract

“…In order to find the possible translations of the seven ambiguous English connectives and based on a large corpus analysis of translations of English discourse connectives into Arabic, we used an automatic method based on alignment between sentences at the word level using GIZA++ [11] and [12]. We experimented with the large UN parallel corpus to find out the Arabic connectives that are aligned to English ones.…”

Section: Towards a Multilingual Act Metricmentioning

confidence: 99%

Assessing the Accuracy of Discourse Connective Translations: Validation of an Automatic Metric

Hajlaoui

Popescu-Belis

2013

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. Automatic metrics for the evaluation of machine translation (MT) compute scores that characterize globally certain aspects of MT quality such as adequacy and fluency. This paper introduces a reference-based metric that is focused on a particular class of function words, namely discourse connectives, of particular importance for text structuring, and rather challenging for MT. To measure the accuracy of connective translation (ACT), the metric relies on automatic word-level alignment between a source sentence and respectively the reference and candidate translations, along with other heuristics for comparing translations of discourse connectives. Using a dictionary of equivalents, the translations are scored automatically, or, for better precision, semiautomatically. The precision of the ACT metric is assessed by human judges on sample data for English/French and English/Arabic translations: the ACT scores are on average within 2% of human scores. The ACT metric is then applied to several commercial and research MT systems, providing an assessment of their performance on discourse connectives.

show abstract

Improved statistical alignment models

Cited by 513 publications

References 4 publications

A new model for persian multi-part words edition based on statistical machine translation

A new model for persian multi-part words edition based on statistical machine translation

Incorporating Linguistic Information to Statistical Word-Level Alignment

Assessing the Accuracy of Discourse Connective Translations: Validation of an Automatic Metric

Contact Info

Product

Resources

About