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

 
Dr. Deyu Zhou School of Computer Science and Engineering, Southeast University, China

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.

 
KMi Seminars
KMi 2013 - A review of the year

Download the KMi 2013 Review of the year iBook to your iOS device or alternatively as a PDF.

Journal | 25 years of knowledge acquisition
 

Social Software is...


Social Software
Social Software can be thought of as "software which extends, or derives added value from, human social behaviour - message boards, musical taste-sharing, photo-sharing, instant messaging, mailing lists, social networking."

Interacting with other people not only forms the core of human social and psychological experience, but also lies at the centre of what makes the internet such a rich, powerful and exciting collection of knowledge media. We are especially interested in what happens when such interactions take place on a very large scale -- not only because we work regularly with tens of thousands of distance learners at the Open University, but also because it is evident that being part of a crowd in real life possesses a certain 'buzz' of its own, and poses a natural challenge. Different nuances emerge in different user contexts, so we choose to investigate the contexts of work, learning and play to better understand the trade-offs involved in designing effective large-scale social software for multiple purposes.