Structure learning for natural langauge processing

Y Ni, C Saunders, S Szedmak, M Niranjan

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

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 andmachine translation (MT), illustrating the effectiveness of the model.
Translated title of the contributionStructure learning for natural langauge processing
Original languageEnglish
Title of host publicationthe 11th IEEE International Workshop on Machine Learning Signal Processing, France
Publication statusPublished - 2009

Bibliographical note

Conference Organiser: MLSP

Fingerprint Dive into the research topics of 'Structure learning for natural langauge processing'. Together they form a unique fingerprint.

Cite this