Semi-automatic grammar induction for bi-directional English-Chinese machine translation

Siu, Kai-Chung; Meng, Huadong

doi:10.21437/eurospeech.2001-643

Cited by 2 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work extends our previous effort in the use of semiautomatically induced grammars for bi-directional English-Chinese machine translation using an example-based approach [1,2]. Our parallel experimental corpora includes the English ATIS-3 Class A sentences (training set, test set 1993 and 1994) with their Chinese translations.…”

Section: Introductionmentioning

confidence: 89%

“…The EBMT module accepts as input the parse structure based on the source language, finds the closest-matching parse structure (and its corresponding sentence) from the training examples in the source language, identifies the parallel sentence in the target language and outputs the parse structure of this parallel sentence. The output parse structure is then used together with the grammar in the target language to generate one or more translations [1]. EBMT has the advantage of being rapidly retargetable to other language pairs, and the use of semi-automatically induced grammars reinforces this advantage.…”

Section: ∑ ∑mentioning

confidence: 99%

“…This is because inflections are absent in Chinese (as the source language), but the appropriate grammar in target language EBMT form needs to be selected for English (as the target language). When multiple inflectional forms are offered by a grammar rule during generation/translation, our original approach simply selects one at random [1]. Our current work attempts to incorporate an enhancement that leverages off parse structures in the example template to make a better selection.…”

Section: ∑ ∑mentioning

confidence: 99%

“…In spatial clustering, words or multi-word entities with similar left and right linguistic contexts are clustered together based on the symmetrized divergence (Div) that is applied to the left and right linguistic contexts of the entity pair. Div incorporates the Kullback-Leibler (KL) distance metric [1,2] (See Equation 1). 1 In general, temporal clustering generates phrasal categories in the grammar and spatial clustering generates semantic categories.…”

Section: Introductionmentioning

confidence: 99%

“…Div incorporates the Kullback-Leibler (KL) distance metric [1,2] (See Equation 1). 1 In general, temporal clustering generates phrasal categories in the grammar and spatial clustering generates semantic categories.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Example-based bi-directional Chinese-English machine translation with semi-automatically induced grammars

Siu¹,

Meng²,

Wong³

2003

8th European Conference on Speech Communication and Technology (Eurospeech 2003)

Self Cite

View full text Add to dashboard Cite

We have previously developed a framework for bi-directional English-to-Chinese/Chinese-to-English machine translation using semi-automatically induced grammars from unannotated corpora. The framework adopts an example-based machine translation (EBMT) approach. This work reports on three extensions to the framework. First, we investigate the comparative merits of three distance metrics (Kullback-Leibler, Manhattan-Norm and Gini Index) for agglomerative clustering in grammar induction. Second, we seek an automatic evaluation method that can also consider multiple translation outputs generated for a single input sentence based on the BLEU metric. Third, our previous investigation shows that Chinese-to-English translation has lower performance due to incorrect use of English inflectional forms -a consequence of random selection among translation alternatives. We present an improved selection strategy that leverages information from the example parse trees in our EBMT paradigm.

show abstract

Section: Introductionmentioning

confidence: 89%

Section: ∑ ∑mentioning

confidence: 99%

Section: ∑ ∑mentioning

confidence: 99%