Amit Bagga, Wlodek Zadronzy, and James Pustejovsky
1. There’s a proliferation of QA systems and NL chat systems on the Web and in intranets (e.g. www.neuromedia.com or www.ask.com). The question arises: how far are these systems from "real" NLU? After all, they seem to follow Eliza. Do they? How do we settle such questions? 2. QA systems typically comprise of an NL understanding systems and a knowledge base/database. Given a user’s query, what is the complexity of retrieving the information from the database? How do we approach this problem? What does it mean that one query is more complex than the other? 3. NLP is in demand. For this demand to be sustained we need a "Moore’s Law for natural language engineering", so that the business community could understand what is possible when and at what price. This panel will address the above three issues from three perspectives: a. lexicon, in particular complexity of lexical semantics. b. text and dialog, and their semantics complexity c. abstract model, which supports the analyses presented in (a) and (b).