Sciweavers

868 search results - page 90 / 174
» Finding Most Likely Solutions
Sort
View
SIGIR
2002
ACM
15 years 13 days ago
Liberal relevance criteria of TREC -: counting on negligible documents?
Most test collections (like TREC and CLEF) for experimental research in information retrieval apply binary relevance assessments. This paper introduces a four-point relevance scal...
Eero Sormunen
106
Voted
TASLP
2002
86views more  TASLP 2002»
15 years 12 days ago
High-level approaches to confidence estimation in speech recognition
Abstract--We describe some high-level approaches to estimating confidence scores for the words output by a speech recognizer. By "high-level" we mean that the proposed me...
Stephen Cox, Srinandan Dasmahapatra
112
Voted
TLT
2010
143views more  TLT 2010»
14 years 11 months ago
Recommendations in Online Discussion Forums for E-Learning Systems
—In this paper, we outline the importance of discussion fora for e-learning applications. Due to a weak structure or size of the discussion forum, recommendations are required in...
Fabian Abel, Ig Ibert Bittencourt, Evandro de Barr...
76
Voted
EMNLP
2010
14 years 10 months ago
Generating Confusion Sets for Context-Sensitive Error Correction
In this paper, we consider the problem of generating candidate corrections for the task of correcting errors in text. We focus on the task of correcting errors in preposition usag...
Alla Rozovskaya, Dan Roth
ICIP
2010
IEEE
14 years 10 months ago
Improving subpixel stereo matching with segment evolution
Segmentation-based approach has shown significant success in stereo matching. By assuming pixels within one image segment belong to the same 3D surface, robust depth estimation ca...
Yao-Jen Chang, Hung-Hsun Liu, Tsuhan Chen