Full Seminar Details

Dr. Deyu Zhou

School of Computer Science and Engineering, Southeast University, China

Dr. Deyu Zhou
Learning Conditional Random Fields from Unaligned Data for Natural Language Understanding
This event took place on Friday 28 October 2011 at 11:30

One of the key tasks in natural language understanding is semantic parsing which maps natural language sentences to complete formal meaning representations. Rule-based approaches are typically domain-specific and often fragile. Statistical approaches are able to accommodate the variations found in real data and hence can in principle be more robust. However, statistical approaches need fully annotated data for training the models. A learning approach to train conditional random fields from unaligned data for natural language understanding is proposed and discussed. The learning approach resembles the expectation maximization algorithm. It has two advantages, one is that only abstract annotations are needed instead of fully word-level annotations, and the other is that the proposed learning framework can be easily extended for training other discriminative models, such as support vector machines, from abstract annotations. The proposed approach has been tested on the DARPA Communicator Data. Experimental results show that it outperforms the hidden vector state (HVS) model, a modified hidden Markov model also trained on abstract annotations.

Watch the webcast replay >>

Jobs

Research Assistant / Associate

Knowledge Media Institute (KMi)
£28,695 - £37,394
Based in Milton Keynes
Temporary contract for 24 months

Declared by Harvard Business Review as the “sexiest job of the 21st century”, data science skills are becoming a key asset to maintain European competitiveness in a global market. Data scientists are, however, a rare breed, e.g. well-known McKinsey...

Tweets

CONTACT US

Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support

COMMENT

If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Systems and Development Team