A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora

Menezes, Arul; Richardson, Stephen D.

doi:10.3115/1118037.1118043

Cited by 53 publications

(51 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides being used in SMT, it is also used in translation lexicon building [8], transfer rule learning [9], example-based machine translation [13], translation memory systems [12], etc.…”

Section: Introductionmentioning

confidence: 99%

Improving Domain-Specific Word Alignment with a General Bilingual Corpus

Wu¹,

Wang²

2004

Machine Translation: From Real Users to Research

View full text Add to dashboard Cite

Abstract. In conventional word alignment methods, some employ statistical models or statistical measures, which need large-scale bilingual sentencealigned training corpora. Others employ dictionaries to guide alignment selection. However, these methods achieve unsatisfactory alignment results when performing word alignment on a small-scale domain-specific bilingual corpus without terminological lexicons. This paper proposes an approach to improve word alignment in a specific domain, in which only a small-scale domain-specific corpus is available, by adapting the word alignment information in the general domain to the specific domain. This approach first trains two statistical word alignment models with the large-scale corpus in the general domain and the small-scale corpus in the specific domain respectively, and then improves the domain-specific word alignment with these two models. Experimental results show a significant improvement in terms of both alignment precision and recall, achieving a relative error rate reduction of 21.96% as compared with state-of-the-art technologies.

show abstract

“…Besides being used in SMT, it is also used in translation lexicon building [8], transfer rule learning [9], example-based machine translation [13], translation memory systems [12], etc.…”

Section: Introductionmentioning

confidence: 99%

Improving Domain-Specific Word Alignment with a General Bilingual Corpus

Wu¹,

Wang²

2004

Machine Translation: From Real Users to Research

View full text Add to dashboard Cite

show abstract

“…This requires syntactically parsing these corpora and aligning them on the constituent level, producing a collection of parallel treebanks. Various systems have been developed for non-terminal constituent alignment, either making use of hand-crafted rules (Menezes and Richardson, 2001;Groves et al, 2004) or fully unsupervised methods (Zhechev and Way, 2008;Lavie et al, 2008). We have opted to use Lingua-Align, a supervised tree-to-tree aligner implementing discriminative models (Tiedemann, 2010).…”

Section: Introductionmentioning

confidence: 99%

Large aligned treebanks for syntax-based machine translation

Kotzé

Vandeghinste

Martens

et al. 2016

Lang Resources & Evaluation

View full text Add to dashboard Cite

We present a collection of parallel treebanks that have been automatically aligned on both the terminal and the nonterminal constituent level for use in syntax-based machine translation. We describe how they were constructed and applied to a syntax-and example-based machine translation system called Parse and Corpus-Based Machine Translation (PaCo-MT). For the language pair Dutch to English, we present evaluation scores of both the nonterminal constituent alignments and the MT system itself, and in the latter case, compare them with those of Moses, a current state-of-the-art statistical MT system, when trained on the same data.

show abstract

“…Along with the efforts made to accumulate bilingual corpora for many language pairs, quite a few machine translation (MT) systems that automatically construct their knowledge from corpora have been proposed (Brown et al, 1993;Menezes and Richardson, 2001;Imamura, 2002). However, if we use corpora without any restriction, redundant rules are acquired due to translation varieties.…”

Section: Introductionmentioning

confidence: 99%

Automatic Construction of Machine Translation Knowledge Using Translation Literalness

Imamura¹,

Sumita²,

Matsumoto³

2004

Journal of Natural Language Processing

View full text Add to dashboard Cite

When machine translation (MT) knowledge is automatically constructed from bilingual corpora, redundant rules are acquired due to translation variety. These rules increase ambiguity or cause incorrect MT results. To overcome this problem, we constrain the sentences used for knowledge extraction to "the appropriate bilingual sentences for the MT." In this paper, we propose a method using translation literalness to select appropriate sentences or phrases. The translation correspondence rate (TCR) is defined as the literalness measure.Based on the TCR, two automatic construction methods are tested. One is to filter the corpus before rule acquisition. The other is to split the acquisition process into two phases, where a bilingual sentence is divided into literal parts and the other parts before different generalizations are applied. The effects are evaluated by the MT quality, and about 4.9% of MT results were improved by the latter method.

show abstract

A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora

Cited by 53 publications

References 13 publications

Improving Domain-Specific Word Alignment with a General Bilingual Corpus

Improving Domain-Specific Word Alignment with a General Bilingual Corpus

Large aligned treebanks for syntax-based machine translation

Automatic Construction of Machine Translation Knowledge Using Translation Literalness

Contact Info

Product

Resources

About