In this paper, we present the results of our investigation into phrase-based statistical machine translation from English into Turkish – an agglutinative language with very productive inflectional and derivational word-formation processes. We investigate different representational granularities for morphological structure and find that (i) representing both Turkish and English at the morpheme-l...

We investigated how Taiwanese diminutive suffix -a is phonetically realized in both juncture and context positions. As a grammatical morpheme, suffix -a is similar to Mandarin diminutive suffix -zi as in yi-zi “chair”. While Mandarin suffix -zi always has a neutral tone or belongs to an unstressed syllable, Taiwanese -a is widely accepted as having a full tone. However, due to the same function...

A system for large vocabulary continuous speech recognition of highly inflectional language is introduced. Word-based recognition approach is compared with a morpheme-based recognition system. An experiment involving Czech N-best rescoring has been performed with encouraging results.

Korean as an agglutinative language shows its proper types of difficulties in morphological disambiguation, since a large number of its ambiguities comes from the stemming while most of ambiguities in French or English are related to the categorization of a morpheme. The current Korean morphological disambiguation systems adopt mainly statistical methods and some of them use rules in the postpr...

Speech recognition systems for languages with a rich in ectional morphology (like German) su er from the limitations of a word{based full{form lexicon. Although the morphological and acoustical knowledge about words is coded implicitly within the lexicon entries (which are usually closely related to the orthography of the language at hand) this knowledge is usually not explicitly available for ...

BACKGROUND One of the barriers for the effective use of computerized health-care related text is the ambiguity of abbreviations. To date, the task of disambiguating abbreviations has been treated as a classification task based on surrounding words. Application of this framework for languages that have no word boundaries requires pre-processing to segment a sentence into separate word sequences....

The Hebrew root morpheme typically consists of three consonants. Hebrew allows a gemination of a root consonant, but constrains its location [McCarthy, J. (1979). Formal problems in semitic phonology and morphology. Cambridge, MA; MIT Ph.D. dissertation. Distributed by Indiana University Linguistics Club. Garland Press, New York, 1985]. A gemination of a root-consonant is permitted at the end o...

For the computer, word forms in an online text are simply letter sequences between blanks. A rule-based automatic language analyses presupposes, however, that the computer can recognize the individual word forms. This includes assigning the base form (lemmatization) and determining the morphosyntactic properties (categorization). It is shown that there are three principled methods of automatic ...