Modern models of relation extraction for tasks like ACE are based on supervised learning of relations from small hand-labeled corpora. We investigate an alternative paradigm that ...
Mike Mintz, Steven Bills, Rion Snow, Daniel Jurafs...
To improve the process of user information retrieval, we propose the concept of a latent semantic map (LSM), along with a method of generating this map. The novel aspect of the LS...
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
We present a weakly supervised approach to automatic Ontology Population from text and compare it with other two unsupervised approaches. In our experiments we populate a part of ...
This paper explores the idea of using contexts to support more efficient information search in Topic Maps-based digital libraries. The notion of context is d as abstraction of grou...