Sciweavers

4660 search results - page 761 / 932
» Learning from imperfect data
Sort
View
EMNLP
2010
13 years 7 months ago
Function-Based Question Classification for General QA
In contrast with the booming increase of internet data, state-of-art QA (question answering) systems, otherwise, concerned data from specific domains or resources such as search e...
Fan Bu, Xingwei Zhu, Yu Hao, Xiaoyan Zhu
ICDM
2010
IEEE
186views Data Mining» more  ICDM 2010»
13 years 7 months ago
MoodCast: Emotion Prediction via Dynamic Continuous Factor Graph Model
Human emotion is one important underlying force affecting and affected by the dynamics of social networks. An interesting question is "can we predict a person's mood base...
Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, Jing...
SIGDIAL
2010
13 years 7 months ago
Towards an Empirically Motivated Typology of Follow-Up Questions: The Role of Dialogue Context
A central problem in Interactive Question Answering (IQA) is how to answer Follow-Up Questions (FU Qs), possibly by taking advantage of information from the dialogue context. We a...
Manuel Kirschner, Raffaella Bernardi
ICCAD
2009
IEEE
96views Hardware» more  ICCAD 2009»
13 years 7 months ago
PSTA-based branch and bound approach to the silicon speedpath isolation problem
The lack of good "correlation" between pre-silicon simulated delays and measured delays on silicon (silicon data) has spurred efforts on so-called silicon debug. The ide...
Sari Onaissi, Khaled R. Heloue, Farid N. Najm
CROSSROADS
2010
13 years 4 months ago
Massive multiplayer human computation for fun, money, and survival
Crowdsourcing is an effective tool to solve hard tasks. By bringing 100,000s of people to work on simple tasks that only humans can do, we can go far beyond traditional models of ...
Lukas Biewald