A framework for MT and multilingual NLG systems based on uniform lexico-structural processing

Lavoie, Benoit; Kittredge, Richard; Korelsky, Tanya; Rambow, Owen

doi:10.3115/974147.974156

Cited by 13 publications

(10 citation statements)

References 7 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our system, the conversion, transfer and realization is done uniformly via lexico-structural processing ( 5]). The Korean parsing is done using Yoon's statistical Korean dependency parser ( 12]), the English parsing is done using the Collins parser ( 2]) and the Korean and English realization is done using RealPro ( 6]).…”

Section: Fig 2 Dsynts For John Often Eats Beansmentioning

confidence: 99%

“…The current implementation and processing of the transfer, conversion and generation rules is done uniformly, using a syntactic lexico-structural based framework ( 5]). Declarative transformation speci cations indicate how the lexemes and their relevant syntactic structures (essentially, their syntactic projection along with syntactic/semantic features) are mapped from one level to another.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System

Han

Lavoie

Palmer

et al. 2000

Envisioning Machine Translation in the Information Future

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes an approach for handling structural divergences and recovering dropped arguments in an implemented Korean to English machine translation system. The approach relies on canonical predicate-argument structures (or dependency structures), which p r o vide a suitable pivot representation for the handling of structural divergences and the recovery of dropped arguments. It can also be converted to and from the interface representations of many o -the-shelf parsers and generators.

show abstract

Section: Fig 2 Dsynts For John Often Eats Beansmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System

Han

Lavoie

Palmer

et al. 2000

Envisioning Machine Translation in the Information Future

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to convert Bangla sentence to UNL expressions firstly, we have gone through Universal Networking Language (UNL) [5,6] where we have learnt about UNL expression, Relations, Attributes, Universal Words, UNL Knowledge Base, Knowledge Representation in UNL, Logical Expression in UNL and UNL systems [7,8]. All these are key factors for preparing Bangla word dictionary, enconversion and deconversion rules in order to convert a natural language sentence (Bangla sentence) into UNL expressions.…”

Section: Methodsmentioning

confidence: 99%

Finding Universal Word for Bangla Language: Attribute Analysis Approach

Hasan¹,

Das²

2011

IJCA

View full text Add to dashboard Cite

Universal natural language (UNL) deals with communication across nations of different languages. It covers many different related disciplines which are linguistic, epistemology etc. UNL helps to overcome the language barrier among people of different nations to solve problems of globalization and geopolitical interdependence. This paper examines bangla root words semantically to find out the universal words according to the usage of words into sentences in relation to the universal network language. The paper also shows different techniques to find the semantic attributes which are the indicators to make rule set. Also, it discusses semantic coverage issues for Bangla to explore the development of universal network language.

show abstract

“…Since translation divergences require a combination of lexical and structural manipulations, they are most typically handled in symbolic MT systems through the use of transfer rules (Han et al 2000;Lavoie et al 2000). 7 A pure transfer approach is a brute force attempt to manually encode all translation divergences in a transfer lexicon (Dorr et al 1999).…”

Section: Handling Translation Divergencesmentioning

confidence: 99%

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

A framework for MT and multilingual NLG systems based on uniform lexico-structural processing

Cited by 13 publications

References 7 publications

Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System

Handling Structural Divergences and Recovering Dropped Arguments in a Korean/English Machine Translation System

Finding Universal Word for Bangla Language: Attribute Analysis Approach

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

Contact Info

Product

Resources

About