Bridging the inflection morphology gap for Arabic statistical machine translation

Zollmann, Andreas; Venugopal, Ashish; Vogel, Stephan

doi:10.3115/1614049.1614100

Cited by 33 publications

(23 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also demonstrated gains in MT quality through a combination of different preprocessing schemes. Additional similar results were reported using specific preprocessing schemes and techniques (Och 2005;El Isbihani et al 2006;Riesa and Yarowsky 2006;Zollmann et al 2006).…”

Section: Morphology-based Approachessupporting

confidence: 68%

Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Habash

Dorr

Monz

2009

Machine Translation

View full text Add to dashboard Cite

The last few years have witnessed an increasing interest in hybridizing surface-based statistical approaches and rule-based symbolic approaches to machine translation (MT). Much of that work is focused on extending statistical MT systems with symbolic knowledge and components. In the brand of hybridization discussed here, we go in the opposite direction: adding statistical bilingual components to a symbolic system. Our base system is Generation-heavy machine translation (GHMT), a primarily symbolic asymmetrical approach that addresses the issue of Interlingual MT resource poverty in source-poor/target-rich language pairs by exploiting symbolic and statistical target-language resources. GHMT's statistical components are limited to target-language models, which arguably makes it a simple form of a hybrid system. We extend the hybrid nature of GHMT by adding statistical bilingual components. We also describe the details of retargeting it to Arabic-English MT. The morphological richness of Arabic brings several challenges to the hybridization task. We conduct an extensive evaluation of multiple system variants. Our evaluation shows that this new variant of GHMT-a primarily symbolic system extended with monolingual and bilingual statistical components-has a higher degree of grammaticality than a phrase-based statistical MT system, where grammaticality is measured in terms of correct verb-argument realization and long-distance dependency translation.

show abstract

Section: Morphology-based Approachessupporting

confidence: 68%

Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Habash

Dorr

Monz

2009

Machine Translation

View full text Add to dashboard Cite

show abstract

“…Integrating the previous researches [1][2][3][4][5][6][7][8][9][10], a lot of literatures have reported label corpus automatic achieving study aiming at word sense disambiguation in a monolingual. Different from tasks of word sense disambiguation, Uyghur translation disambiguation is to solve the correct translation of Uyghur ambiguous terms in target language in nature, i.e., to find the most suitable Chinese translation for Uyghur ambiguous terms according to the context.…”

Section: Introductionmentioning

confidence: 99%

Uyghur-Chinese Translation Disambiguation Method Research Based on Knowledge Automatic-Acquisition

Ren¹,

Yang²,

Xu³

2014

TOCSJ

View full text Add to dashboard Cite

This thesis studies the disambiguation method in Uyghur-Chinese translation, and proposes the design philosophy of automatic-acquisition in translation label library aiming at the deficiency of disambiguation corpus in Uyghur. It refers to the existing Uyghur-Chinese bilingual dictionary, Chinese corpus and the Internet, and acquires the corresponding Chinese translation label examples to Uyghur automatically. On this basis, this thesis designs a Uyghur-Chinese disambiguation model, and refines the meaning probability definition based on HMM model. It increases the model's backwards-dependence, and the model's ability to obtain contextual information. To use the model to learn disambiguation knowledge from translation label corpus can eliminate the ambiguity in new Uyghur ambiguous words. From the experiment result, it can prove that the Uyghur-Chinese translation disambiguation framework based on automatically acquired corpus is effective, and increases with the increasing of the scale of translation label corpus, degree of accuracy of the disambiguation result also increases accordingly.

show abstract

“…Lee [21] uses a morphologically analyzed and tagged parallel corpus for Arabic-English statistical machine translation. Zolmann et al [22] also exploit morphology in Arabic-English statistical machine translation. Popovic and Ney [23] investigate improving translation quality from inflected languages by using stems, suffixes and part-of-speech tags.…”

Section: Exploiting Morphologymentioning

confidence: 99%

Exploiting Morphology and Local Word Reordering in English-to-Turkish Phrase-Based Statistical Machine Translation

El-Kahlout

Oflazer

2010

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkish-an agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for English-Turkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the -best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62% relative.Index Terms-Complex morphology, English, statistical machine translation (SMT), Turkish, word reordering.

show abstract

Bridging the inflection morphology gap for Arabic statistical machine translation

Cited by 33 publications

References 10 publications

Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Symbolic-to-statistical hybridization: extending generation-heavy machine translation

Uyghur-Chinese Translation Disambiguation Method Research Based on Knowledge Automatic-Acquisition

Exploiting Morphology and Local Word Reordering in English-to-Turkish Phrase-Based Statistical Machine Translation

Contact Info

Product

Resources

About