111 search results - page 12 / 23 » LivingKnowledge: Kernel Methods for Relational Learning and ... |
161
Voted
ACL
2010
15 years 4 months ago
2010
We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...
167
Voted
NAACL
2010
15 years 4 months ago
2010
We describe tree edit models for representing sequences of tree transformations involving complex reordering phenomena and demonstrate that they offer a simple, intuitive, and eff...
168
Voted
ECML
2006
Springer
15 years 10 months ago
2006
Springer
Abstract. Conditional Random Fields (CRFs) provide a powerful instrument for labeling sequences. So far, however, CRFs have only been considered for labeling sequences over flat al...
165
Voted
EMNLP
2006
15 years 7 months ago
2006
This paper demonstrates how unsupervised techniques can be used to learn models of deep linguistic structure. Determining the semantic roles of a verb's dependents is an impo...
203
Voted
EMNLP
2008
15 years 7 months ago
2008
Complex questions that require inferencing and synthesizing information from multiple documents can be seen as a kind of topicoriented, informative multi-document summarization. I...