Fourteenth Conference on Computational Natural Language Learning, CoNLL-2010

Fourteenth Conference on Computational Natural Language Learning, CoNLL-2010
Uppsala, Sweden
July 15-16, 2010

CoNLL is the yearly international conference on natural language learning organized by SIGNLL (the ACL Special Interest Group on Natural Language Learning). This year, CoNLL will be collocated with ACL 2010 in Uppsala, Sweden.

Important Dates

• Paper submission deadline: March 8, 2010, 23:59 GMT
• Notification of acceptance: April 15
• Camera-ready copy deadline: May 6
• Conference: July 15-16

Topics

The PC invites submission of papers about natural language learning topics including:

• Supervised, unsupervised and semi-supervised machine learning methods applied to natural language
• Computational models of human language acquisition and processing
• Optimisation methods and inference algorithms for natural language
• Active learning for natural language processing tasks
• Computational learning theory analysis of language learning
• Empirical and theoretical comparisons of language learning methods including novel evaluation methods
• Computational models of language evolution and historical change
• Algorithms for grammatical inference applied to natural language

Invited Speakers

• Lillian Lee (Cornell University)
• Zoubin Gharamani (University of Cambridge)

Special Topic of Interest

This year in CoNLL-2010 the special topic of interest is: Grammar induction

Shared Task

"Learning to detect hedges and their scope in natural language texts"

In Natural Language Processing (NLP) - in particular, in Information Extraction (IE) - many applications aim at extracting factual information from text. In order to distinguish facts from unreliable or uncertain information, linguistic devices such as hedges (indicating that authors do not or cannot back up their opinions/statements with facts) have to be identified. Applications should handle detected speculative parts in a different manner. Hedge detection has received considerable interest recently in the biomedical NLP community, including research papers addressing the detection of hedge devices in biomedical texts, and some recent work on detecting the in-sentence scope of hedge cues in text. Exploiting the hedge scope annotated BioScope corpus and publicly available Wikipedia texts, the goals of the Shared Task are 1) learning to detect hedge cues in natural language texts and 2) learning to resolve the in-sentence scope of hedge cues.