I built or co-built the following demos.

Information Extraction

Information extraction is the technology that transfers human-readable documents into machine-readable data. Useful and important information can be extracted from lots of unorganized documents such as news articles and email, and stored in databases. Then, it is relatively easy to get answers to the type of structured queries that ordinary search engines do not support. We demonstrate the technology by showing its ability to extracts specific phrases of interest in two types of documents --- seminar announcements and job postings.

Related Paper:

1. Relational Learning via Propositional Algorithms: An Information Extraction Case Study
   Proc. of the International Joint Conference on Artificial Intelligence (IJCAI-01)
   with D. Roth

Semantic Role Labeling

Beyond the syntactical analysis of natural language sentences is the extraction of its semantic information. Semantic role labeling is one of such tasks which identifies the verb and argument structure in natural language sentences, and is an important task toward natural language understanding.

Related Papers:

1. The Necessity of Syntactic Parsing for Semantic Role Labeling
   Proc. of the International Joint Conference on Artificial Intelligence (IJCAI-05)
   with V. Punyakanok, D. Roth
2. Generalized Inference with Multiple Semantic Role Labeling Systems
   Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL-05)
   with V. Punyakanok, D. Roth
3. Semantic Role Labeling via Integer Linear Programming Inference.
   Proc. of the International Conference on Computational Linguistics (COLING-04)
   with V. Punyakanok, D. Roth, D. Zimak
4. Semantic Role Labeling via Generalized Inference over Classifiers.
   Proc. of the Annual Conference on Computational Natural Language Learning (CoNLL-04)
   with V. Punyakanok, D. Roth, Y. Tu, D. Zimak

[Home] [Education] [Experience] [Publications] [Presentations] [Demos] [Services] [Links]