Sciweavers

1209 search results - page 138 / 242
» Using Prosodic Features in Language Models for Meetings
Sort
View
101
Voted
JCDL
2005
ACM
100views Education» more  JCDL 2005»
15 years 9 months ago
Automatic extraction of titles from general documents using machine learning
In this paper, we propose a machine learning approach to title extraction from general documents. By general documents, we mean documents that can belong to any one of a number of...
Yunhua Hu, Hang Li, Yunbo Cao, Dmitriy Meyerzon, Q...
147
Voted
SIGIR
2003
ACM
15 years 8 months ago
Table extraction using conditional random fields
The ability to find tables and extract information from them is a necessary component of data mining, question answering, and other information retrieval tasks. Documents often c...
David Pinto, Andrew McCallum, Xing Wei, W. Bruce C...
144
Voted
SDL
2007
171views Hardware» more  SDL 2007»
15 years 5 months ago
Model Driven Development and Code Generation: An Automotive Case Study
Describing an application as a simple composition of services allows advanced features that exploit different platforms to be conceived e formalized at a high abstraction level. S...
Michele Banci, Alessandro Fantechi, Stefania Gnesi...
164
Voted
ACL
2003
15 years 5 months ago
Improved Source-Channel Models for Chinese Word Segmentation
This paper presents a Chinese word segmentation system that uses improved sourcechannel models of Chinese sentence generation. Chinese words are defined as one of the following fo...
Jianfeng Gao, Mu Li, Changning Huang
133
Voted
SPEECH
2008
142views more  SPEECH 2008»
15 years 3 months ago
Combined speech enhancement and auditory modelling for robust distributed speech recognition
The performance of automatic speech recognition (ASR) systems in the presence of noise is an area that has attracted a lot of research interest. Additive noise from interfering no...
Ronan Flynn, Edward Jones