Latest News and Events

The SAMSI-FODAVA Workshop on Interactive Visualization and Analysis of Massive Data will be held on December 10-12, 2012.
Posted: October 02, 2012
The FODAVA Annual Meeting will immediately follow (Dec 12-13) the SAMSI/FODAVA joint workshop at the same location.
Posted: September 05, 2012
Many of the modern data sets such as text and image data can be represented in high-dimensional vector spaces and have benefited from computational methods that utilize advanced techniques from num
Posted: June 30, 2012

Relation Extraction with Relation Topics

Chang Wang

Detecting semantic relations in text is very useful in both information retrieval and question answering because it enables knowledge bases to be leveraged to score passages and retrieve candidate answers. In this talk, I will present a novel transfer learning approach to the semantic relation detection problem.

Instead of relying only on the training instances for a new relation, we leverage the knowledge learned from previously trained relation detectors. Specifically, we detect a new semantic relation by projecting the new relation's training instances onto a lower dimension topic space constructed from existing relation detectors through a three step process. First, we construct a large relation repository of more than 7,000 relations from Wikipedia. Second, we construct a set of non-redundant relation topics defined at multiple scales using diffusion wavelets from the relation repository to characterize the existing relations. Similar to the topics defined over words, each relation topic is an interpretable multinomial distribution over the existing relations. Third, we integrate the relation topics in a kernel function, and use it together with SVM to construct detectors for new relations.

The experimental results on Wikipedia and ACE data have confirmed that background-knowledge-based topics generated from the Wikipedia relation repository can significantly improve the performance over the state-of-the-art relation detection approaches.

Chang Wang is a research scientist at IBM Research. He is currently working on DeepQA (Watson) project. The DeepQA project is to push question answering technology to levels of performance previously unseen and demonstrate the technology by playing Jeopardy! at the level of a human champion. Chang's research areas include Machine Learning (Manifold Learning, Representation Learning, Multiscale Analysis); Knowledge Transfer Across Domains; and Application of Machine Learning in Natural Language Processing (NLP) and Information Retrieval.