Sciweavers

11538 search results - page 351 / 2308
» From Text to Knowledge
Sort
View
ACL
2012
13 years 9 months ago
Coreference Semantics from Web Features
To address semantic ambiguities in coreference resolution, we use Web n-gram features that capture a range of world knowledge in a diffuse but robust way. Specifically, we exploi...
Mohit Bansal, Dan Klein
ICDE
2003
IEEE
133views Database» more  ICDE 2003»
16 years 8 months ago
Text Joins for Data Cleansing and Integration in an RDBMS
An organization's data records are often noisy because of transcription errors, incomplete information, lack of standard formats for textual data or combinations thereof. A f...
Luis Gravano, Panagiotis G. Ipeirotis, Nick Koudas...
MM
2003
ACM
142views Multimedia» more  MM 2003»
15 years 12 months ago
Synchronization of lecture videos and electronic slides by video text analysis
An essential goal of structuring lecture videos captured in live presentation is to provide a synchronized view of video clips and electronic slides. This paper presents an automa...
Feng Wang, Chong-Wah Ngo, Ting-Chuen Pong
ICDAR
1999
IEEE
15 years 11 months ago
Text/Graphics Separation using Agent-based Pyramid Operations
This paper describes a document image analysis system using multiple agents working on a pyramid structure to separate text from graphics in the image. Text strings appear as diff...
Chew Lim Tan, Bo Yuan, Weihua Huang, Qian Wang, Zh...
LREC
2008
70views Education» more  LREC 2008»
15 years 8 months ago
Process Model for Composing High-quality Text Corpora
The Teko corpus composing model offers a decentralized, dynamic way of collecting high-quality text corpora for linguistic research. The resulting corpus consists of independent t...
Mikko Lounela