========== CALL FOR PAPERS ==========
Question answering is a central task in natural language processing (NLP). Unlike other NLP tasks, it also is easy for non-experts to understand when question answering systems perform well (or fail). The goal of this workshop is to bring the community together to discuss the state of the art of question answering and interactively compete with top human trivia masters. To this end, we welcome submissions on topics that include but are not limited to:
- Systems designed for specific factoid / non-factoid / community QA tasks - Training algorithms or modules that can benefit a variety of QA systems - Analysis of particular types of questions that are challenging for existing systems - New QA datasets / tasks - Methods for evaluating QA systems
We solicit previously unpublished work following the NAACL 2016 formatting guidelines.
Papers should have at most 6 pages of content, not including references. There is no constraint on the size of the reference list. Submissions should be anonymous and not disclose in any way the identity of the author(s).
Papers should be submitted to http://softconf.com/naacl2016/HCQA16 by April 11, 2016. Accepted papers will be presented as either posters or talks.
More information: https://sites.google.com/a/colorado.edu/2016-naacl-ws-human-computer-qa/home
February: Release training data, announce development server April 11: Paper submission deadline April 18: Paper notifications April 25: Camera ready deadline May 1: Server available for submitting final system May 30: Deadline for connecting to server and submit their systems June 11/12: Humans compete with submitted systems (to be recorded) June 16: Final game between best human team and best computer system
=====Shared Task: Question Answering Competition=====
In addition to invited talks from experts, selected oral talks from submissions, and a poster session, we are also organizing a dual computer-human tournament to test entrants’ question answering systems against each other and against the top human trivia masters. The final match between the top computer system and the top human team will be part of the workshop. See this page for training data, deadlines, and other details.
Mohit Iyyer He He Jordan Boyd-Graber Hal Daumé
Mohit Bansal Kevin Gimpel Edward Grefenstette Sanda Harabagiu Mandar Joshi Karthik Narasimhan Arvind Neelakantan Mrinmaya Sachan Tomek StrzalkowskiRichard Socher Christina Unger Yi Yang Wen-Tau Yih Luke Zettlemoyer -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3024 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20160404/49a8ba94/attachment.txt>