Analysis of unknown words through morphological decomposition

Black, Alan W.; Plassche, J. van de; Williams, Briony

doi:10.3115/977180.977198

Cited by 6 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When eneounteruig an unknown term, however similar to a known one, the system will not be able to fall softly and produce some kind of reasonably acceptable translation like a human translator does. Similar consideration motives a text-to-speech research on producing pronunciation for an mflulown words through morphological decomposition (Black et al 1991).…”

Section: Introductionmentioning

confidence: 68%

A statistical approach to machine aided translation of terminology banks

Chang

Chang²,

Lin

et al. 1992

Proceedings of the 14th Conference on Computational Linguistics -

View full text Add to dashboard Cite

l]fis paper reports on a new statistical approach to machine aided translation of terminology bank. The text in the bank is hyphenated and then dissected into roots of 1 to 3 syllables. Both hyphenation and dissection are done with a set of initial probabilities of syllables and roots. The probabilities are repeatedly revised using an EM algorithm. Alter each iteration of hyphenation or dissectioh, the resulting syllables and roots are counted subsequently to yield more precise estimation of probability. The set of roots rapidly converges to a set of most likely roots. Preliminary experhuents have shown promising results. From a terminology bank of more than 4,000 terms, the algorithm extracts 223 general and chemical roots, of which 91% are actually roots. The algoritlun dissects a word into roots with aromld 86% hit rate. The set of roots and their "hand-translation are then used iu a compositional translation of the terminology bank. One can expect the translation of terminology bank using this approach to be more cost-effective, consistent, and with a better closure.

show abstract

Section: Introductionmentioning

confidence: 68%

A statistical approach to machine aided translation of terminology banks

Chang

Chang²,

Lin

et al. 1992

Proceedings of the 14th Conference on Computational Linguistics -

View full text Add to dashboard Cite

show abstract

“…In order to deal with it, a general transducer has been designed to relax the need of lemmas in the lexicon. This transducer was initially (Alegria et al 1997) based on the idea used in speech synthesis (Black et al 1991) but now it has been simplified. Daciuk (Daciuk 2000) proposes a similar way when he describes the guessing automaton, but the construction of the automaton is more complex.…”

Section: The General Transducermentioning

confidence: 99%

Using Finite State Technology in Natural Language Processing of Basque

Alegria

Aranzabe

Ezeiza

et al. 2002

Implementation and Application of Automata

View full text Add to dashboard Cite

Abstract. This paper describes the components used in the design and implementation of NLP tools for Basque. These components are based on finite state technology and are devoted to the morphological analysis of Basque, an agglutinative pre-Indo-European language. We think that our design can be interesting for the treatment of other languages. The main components developed are a general and robust morphological analyser/generator and a spelling checker/corrector for Basque named Xuxen. The analyser is a basic tool for current and future work on NLP of Basque, such as the lemmatiser/tagger Euslem, an Intranet search engine or an assistant for verse-making.

show abstract

“…The idea of using regular expressions for morphological analysis is not a novel one. Morphological analysis has been widely used to improve the lexical and error recall of different human language technology applications (Porter, 1980;Black et al, 1991;Kraaij & Pohlmann, 1996;Van Huyssteen & Van Zaanen, 2003). In the context of spelling checkers, lexical recall refers to the recognition of correctly spelled words by the spelling checker, whilst error recall is the accurate rejection of incorrectly spelled words (Starlander & Popescu-Belis, 2002:271).…”

Section: Introductionmentioning

confidence: 99%

The effectiveness of morphological rules for an isiZulu spelling checker

Bosch

Eiselen

2005

South African Journal of African Languages

View full text Add to dashboard Cite

This paper shows how morphological analysis contributes to solving the challenges posed by the development of a spelling checker for an agglutinative language like isiZulu. It demonstrates how the incremental implementation of affix removal rules can be used to derive word forms and enhance the lexical and error recall of the system. In the case of the spelling checker the strategies used are mainly based on the use of regular expressions, and more specifically on a process of stemming.

show abstract

Analysis of unknown words through morphological decomposition

Cited by 6 publications

References 2 publications

A statistical approach to machine aided translation of terminology banks

A statistical approach to machine aided translation of terminology banks

Using Finite State Technology in Natural Language Processing of Basque

The effectiveness of morphological rules for an isiZulu spelling checker

Contact Info

Product

Resources

About