Paper: Social Network Extraction from Texts: A Thesis Proposal

ACL ID P11-3020
Title Social Network Extraction from Texts: A Thesis Proposal
Venue Annual Meeting of the Association of Computational Linguistics
Session Student Session
Year 2011
Authors

In my thesis, I propose to build a system that would enable extraction of social interactions from texts. To date I have defined a compre- hensive set of social events and built a prelim- inary system that extracts social events from news articles. I plan to improve the perfor- mance of my current system by incorporating semantic information. Using domain adapta- tion techniques, I propose to apply my sys- tem to a wide range of genres. By extracting linguistic constructs relevant to social interac- tions, I will be able to empirically analyze dif- ferent kinds of linguistic constructs that peo- ple use to express social interactions. Lastly, I will attempt to make convolution kernels more scalable and interpretable.