We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...
One of the essential functions of natural language is to talk about spatial relationships between objects. Linguistic constructs can express highly complex, relational structures ...
Parisa KordJamshidi, Martijn van Otterlo, Marie-Fr...
For effective retrieval of visual information, statistical learning plays a pivotal role. Statistical learning in such a context faces at least two major mathematical challenges: ...
In this paper, we present a learning framework for the semantic annotation of text documents that can be used as textual cases in case-based reasoning applications. The annotation...
We describe a novel neural network architecture for the problem of semantic role labeling. Many current solutions are complicated, consist of several stages and handbuilt features...