945 search results - page 28 / 189 » On the robustness of primitive words |
161
Voted
NIPS
2008
15 years 7 months ago
2008
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...
143
click to vote
ICDAR
2009
IEEE
15 years 3 months ago
2009
IEEE
We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained "on the fly...
179
Voted
ACL
2011
14 years 9 months ago
2011
Unsupervised vector-based approaches to semantics can model rich lexical meanings, but they largely fail to capture sentiment information that is central to many word meanings and...
192
click to vote
ICTAI
2007
IEEE
16 years 12 days ago
2007
IEEE
Typically, spam filters are built on the assumption that the characteristics of e-mails in the training set is identical to those in individual users’ inboxes on which it will b...
198
click to vote
NOLISP
2007
Springer
16 years 6 days ago
2007
Springer
In this paper we propose a feedforward neural network for syllable recognition. The core of the recognition system is based on a hierarchical architecture initially developed for ...