Structure learning for natural language processing

Author

Ni, Yizhao ; Saunders, Craig J. ; Szedmak, Sandor ; Niranjan, Mahesan

Author_Institution

Sch. of Electron. & Comput. Sci., Univ. of Southampton, Southampton, UK

fYear

2009

fDate

1-4 Sept. 2009

Firstpage

1

Lastpage

6

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 Vector Machine (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.

Keywords

learning (artificial intelligence); natural language processing; support vector machines; Max-Margin Structure model; machine translation task; natural language processing; part-of-speech tagging task; perceptron-based learning approach; structure learning model; support vector machine; Computer science; Entropy; Hidden Markov models; Intersymbol interference; Machine learning; Maximum likelihood estimation; Natural language processing; Support vector machines; Surface-mount technology; Tagging;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning for Signal Processing, 2009. MLSP 2009. IEEE International Workshop on

Conference_Location

Grenoble

Print_ISBN

978-1-4244-4947-7

Electronic_ISBN

978-1-4244-4948-4

Type

conf

DOI

10.1109/MLSP.2009.5306193

Filename

5306193