Sciweavers

120 search results - page 6 / 24
» Language Modeling with Sentence-Level Mixtures
Sort
View
EACL
2009
ACL Anthology
13 years 5 months ago
Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument S
like text summarisation requires a means of producing novel summary sentences. In order to improve the grammaticality of the generated sentence, we model a global (sentence) level...
Stephen Wan, Mark Dras, Robert Dale, Cécile...
ICASSP
2010
IEEE
13 years 8 months ago
Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...
Lukas Burget, Petr Schwarz, Mohit Agarwal, Pinar A...
ACL
2011
12 years 11 months ago
Joint Bilingual Sentiment Classification with Unlabeled Parallel Corpora
Most previous work on multilingual sentiment analysis has focused on methods to adapt sentiment resources from resource-rich languages to resource-poor languages. We present a nov...
Bin Lu, Chenhao Tan, Claire Cardie, Benjamin K. Ts...
IR
2011
12 years 11 months ago
Modeling score distributions in information retrieval
We review the history of modeling score distributions, focusing on the mixture of normal-exponential by investigating the theoretical as well as the empirical evidence supporting i...
Avi Arampatzis, Stephen Robertson
ICMCS
2005
IEEE
169views Multimedia» more  ICMCS 2005»
14 years 1 months ago
Dynamic language model adaptation using latent topical information and automatic transcripts
This paper considers dynamic language model adaptation for Mandarin broadcast news recognition. Both contemporary newswire texts and in-domain automatic transcripts were exploited...
Berlin Chen