This paper describes the Korean speech corpus for train ticket reservation aid system based on speech recognition. Two sets of speech corpus were collected. One was based on human-human(H-H) dialogues and the other was based on human-computer(H-C) dialogues. WOZ(Wizard of Oz) experiment was carried out to collect speech corpus based on H-C spoken dialogue. A total of 298 speaker data was collec...

In this talk we will explore the syntactic structure of the " phrasal " Mandarin bi comparative. We aim to: • motivate the Mandarin comparative morpheme bi as a v head; • argue against Liu's (1996) PP analysis and Xiang's (2005) DegP analysis on syntactic grounds; • explore a neo-Davidsonian event-based conceptualization of comparison. A comparative generally involves two things to be compared,...

This article describes the design and the experimental evaluation of the first Hungarian large vocabulary continuous speech recognition (LVCSR) system. The architecture of the recognition system is based on the recently proposed weighted finite state transducer (WFST) paradigm. The task domain is the recognition of fluently read sentences selected from a major daily newspaper. Recognition perfo...

This article describes the design and the experimental evaluation of the first Hungarian large vocabulary continuous speech recognition (LVCSR) system. The architecture of the recognition system is based on the recently proposed weighted finite state transducer (WFST) paradigm. The task domain is the recognition of fluently read sentences selected from a major daily newspaper. Recognition perfo...

Over the past decades an extraordinary amount of psycholinguistic and neurolinguistic research has been carried out with the aim of understanding the nature of lexical representations and how these representations are accessed as we listen to or read words. The question that drives much of this research is whether the language processing system has access to a morpheme-based route to recognize ...

This study investigates semantic constraints affecting the order of motion morphemes in Mandarin multi-morpheme motion constructions (e.g., tui-hui recede-return). It classifies Chinese motion morphemes into three major types and proposes a “Scalar Specificity Constraint” to account for the order in multi-morpheme motion constructions. The constraint not only provides a better coverage of the d...

We have been developing methods of kanji morpheme analysis for the empirical modelling of terminology. In this paper we discuss the performance of kanji morpheme extraction and kanji sequence decomposition, both based on the same bigram statistics, focusing on the e ect of type-based and token-based trainings. The experiment shows that type-based training gives consistently better performance, ...

The ParaMor algorithm for unsupervised morphology induction, which competed in the 2007 and 2008 Morpho Challenge competitions, does not assign a numeric score to its segmentation decisions. Scoring each character boundary in each word with the likelihood that it falls at a true morpheme boundary would allow ParaMor to adjust the confidence level at which the algorithm proposes segmentations. A...

This paper presents the evaluation of Morpho Challenge Competition 2 (information retrieval). The Competition 1 (linguistic gold standard) is described in a companion paper. In Morpho Challenge 2007, the objective was to design statistical machine learning algorithms that discover which morphemes (smallest individually meaningful units of language) words consist of. Ideally, these are basic voc...