Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

CICLING
2003
Springer

favoriteEmaildiscussreport

146views Natural Language Processing» more CICLING 2003»

A Maximum Entropy Approach for Spoken Chinese Understanding

13 years 9 months ago

A Maximum Entropy Approach for Spoken Chinese Understanding

Download nlpr-web.ia.ac.cn

: In this paper, we present a spoken language understanding method based on the maximum entropy model. We first extract certain features from the corpus, and then train the maximum entropy model with an annotated corpus. We use this model to analyze spoken Chinese into semantic frames. Experiments show that the model can work effectively.

Guodong Xie, Chengqing Zong, Bo Xu

Real-time Traffic

Annotated Corpus | CICLING 2003 | Language Understanding Method | Maximum Entropy Model | Natural Language Processing |

claim paper

Related Content

» A Maximum Entropy Model Based Answer Extraction for Chinese Question Answering

» A New Approach for EnglishChinese Named Entity Alignment

» Simple Features for Chinese Word Sense Disambiguation

» A Chunking Strategy Towards Unknown Word Detection in Chinese Word Segmentation

» MARS A Statistical Semantic Parsing and GenerationBased Multilingual Automatic tRanslation...

» Chinese PartofSpeech Tagging OneataTime or AllatOnce WordBased or CharacterBased

» Iterative Scaling and Coordinate Descent Methods for Maximum Entropy Models

» SubwordBased Tagging for ConfidenceDependent Chinese Word Segmentation

» Semantic confidence calibration for spoken dialog applications

Post Info
More Details (n/a)

Added	06 Jul 2010
Updated	06 Jul 2010
Type	Conference
Year	2003
Where	CICLING
Authors	Guodong Xie, Chengqing Zong, Bo Xu

Comments (0)