Sciweavers

25 search results - page 5 / 5
» The Corpus DIMEx100: transcription and evaluation
Sort
View
ICASSP
2010
IEEE
13 years 6 months ago
Power law discounting for n-gram language models
We present an approximation to the Bayesian hierarchical PitmanYor process language model which maintains the power law distribution over word tokens, while not requiring a comput...
Songfang Huang, Steve Renals
TASLP
2008
149views more  TASLP 2008»
13 years 6 months ago
Using Articulatory Representations to Detect Segmental Errors in Nonnative Pronunciation
Abstract--Motivated by potential applications in second-language pedagogy, we present a novel approach to using articulatory information to improve automatic detection of typical p...
Joseph Tepperman, Shrikanth Narayanan
ICASSP
2011
IEEE
12 years 10 months ago
Sentence simplification for spoken language understanding
In this paper, we present a sentence simplification method and demonstrate its use to improve intent determination and slot filling tasks in spoken language understanding (SLU) ...
Gökhan Tür, Dilek Hakkani-Tür, Larr...
LREC
2010
160views Education» more  LREC 2010»
13 years 7 months ago
FrAG, a Hybrid Constraint Grammar Parser for French
This paper describes a hybrid tagger/parser for French (FrAG), and presents results from ongoing development work, corpus annotation and evaluation. The core of the system is a se...
Eckhard Bick
NAACL
2007
13 years 7 months ago
Entity Extraction is a Boring Solved Problem - Or is it?
This paper presents empirical results that contradict the prevailing opinion that entity extraction is a boring solved problem. In particular, we consider data sets that resemble ...
Marc Vilain, Jennifer Su, Suzi Lubar