Paper: LexNet: A Graphical Environment For Graph-Based NLP

ACL ID P06-4012
Title LexNet: A Graphical Environment For Graph-Based NLP
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2006

This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the Uni- versity of Michigan. LexNet includes LexRank (for text summarization), bi- ased LexRank (for passage retrieval), and TUMBL (for binary classification). All tools in the collection are based on random walks on lexical graphs, that is graphs where different NLP objects (e.g. , sen- tences or phrases) are represented as nodes linked by edges proportional to the lexi- cal similarity between the two nodes. We will demonstrate these tools on a variety of NLP tasks including summarization, ques- tion answering, and prepositional phrase attachment.