STRUCTURE LEARNING FOR NATURAL LANGUAGE PROCESSING


Ni, Yizhao, Saunders, Craig, Szedmak, Sandor and Niranjan, Mahesan (2009) STRUCTURE LEARNING FOR NATURAL LANGUAGE PROCESSING At IEEE Workshops on Machine Learning for Signal Processing, 2009, France. 02 - 04 Sep 2009.

Download

[img] PDF structure_learning_for_NLP.pdf - Version of Record
Download (374kB)

Description/Abstract

We applied a structure learning model, Max-Margin Structure (MMS), to natural language processing (NLP) tasks, where the aim is to capture the latent relationships within the output language domain. We formulate this model as an extension of multi–class Support VectorMachine (SVM) and present a perceptron–based learning approach to solve the problem. Experiments are carried out on two related NLP tasks: part–of–speech (POS) tagging and machine translation (MT), illustrating the effectiveness of the model.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Event Dates: Sep 2, 2009 - Sep 4, 2009
Venue - Dates: IEEE Workshops on Machine Learning for Signal Processing, 2009, France, 2009-09-02 - 2009-09-04
Organisations: Southampton Wireless Group
ePrint ID: 270915
Date :
Date Event
2009Published
Date Deposited: 23 Apr 2010 10:51
Last Modified: 17 Apr 2017 18:27
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/270915

Actions (login required)

View Item View Item