62 |
Lexical triggers and latent semantic analysis for crosslingual language model adaptation
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/talip04.pdf (2004)
|
|
BASE
|
|
Show details
|
|
63 |
Contemporaneous Text as Side-Information in Statistical Language Modeling
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/csl04.pdf (2004)
|
|
BASE
|
|
Show details
|
|
64 |
Cross-lingual latent semantic analysis for LM
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/icassp04.pdf (2004)
|
|
BASE
|
|
Show details
|
|
66 |
Language Model Adaptation Using Cross-Lingual Information
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/euro03.pdf (2003)
|
|
BASE
|
|
Show details
|
|
67 |
Cross-Lingual Lexical Triggers in Statistical Language Modeling
|
|
|
|
In: http://acl.ldc.upenn.edu/W/W03/W03-1003.pdf (2003)
|
|
BASE
|
|
Show details
|
|
68 |
Cross-Lingual Lexical Triggers in Statistical Language Modeling
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/emnlp03.pdf (2003)
|
|
BASE
|
|
Show details
|
|
69 |
Contemporaneous Text as Side-Information in Statistical Language Modeling
|
|
|
|
In: http://www.clsp.jhu.edu/~sanjeev/Pubs/CSL2003b.pdf (2003)
|
|
Abstract:
We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language processing applications. In particular, we investigate the use of text from a resource-rich language to sharpen language models for processing a news story or article in a language with scarce linguistic resources. We demonstrate that even with fairly crude cross-language information retrieval and simple machine translation, one can construct story-specific Chinese language models which exploit cues from a side-corpus of English newswire to significantly improve the performance of language models estimated from a static Chinese corpus. Our investigations cover cases when the amount of available Chinese text is small, and a case when a large Chinese text corpus is available. We examine the e#ectiveness of our techniques both when the side-corpus contains English documents that are near-translations of the Chinese documents being processed, and when the English side-corpus is merely from contemporaneous and independent news sources. We present experimental results for automatic transcription of speech from the Mandarin Broadcast News corpus.
|
|
Keyword:
Automatic speech recognition; Multi-lingual processing; Resource-deficient; Statistical language modeling
|
|
URL: http://www.clsp.jhu.edu/~sanjeev/Pubs/CSL2003b.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.5345
|
|
BASE
|
|
Hide details
|
|
70 |
Making miracles: Interactive translingual search for cebuano and hindi
|
|
|
|
In: http://www.sis.pitt.edu/~daqing/docs/talip-final.pdf (2003)
|
|
BASE
|
|
Show details
|
|
71 |
Cross-Lingual Lexical Triggers in Statistical Language Modeling
|
|
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
72 |
Maximum Entropy Language Modeling with Non-Local and Syntactic Dependencies
|
|
|
|
In: http://www.cs.jhu.edu/~junwu/gbo.ps (2002)
|
|
BASE
|
|
Show details
|
|
73 |
Making Indian Language Legacy Documents Accessible Via Web
|
|
|
|
In: http://www.ee.iitb.ernet.in/uma/~ncc2002/proc/NCC-2002/pdf/n074.pdf (2002)
|
|
BASE
|
|
Show details
|
|
74 |
Using Cross-Language Cues For Story-Specific Language Modeling
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/icslp02.pdf (2002)
|
|
BASE
|
|
Show details
|
|
75 |
Smoothing Issues in the Structured Language Model
|
|
|
|
In: http://cs.jhu.edu/~junwu/eurospeech01.ps (2001)
|
|
BASE
|
|
Show details
|
|
76 |
Smoothing Issues in the Structured Language Mode
|
|
|
|
In: http://www.clsp.jhu.edu/~woosung/pdf/euro01.pdf (2001)
|
|
BASE
|
|
Show details
|
|
80 |
Pronunciation modeling by sharing Gaussian densities across phonetic models,” Computer Speech and Language
|
|
|
|
In: http://busim.ee.boun.edu.tr/~speech/publications/Speech_Recognition/eurospeech99.pdf (2000)
|
|
BASE
|
|
Show details
|
|
|
|