The application of structured learning in natural language processing

Y Ni, C Saunders, S Szedmak, M Niranjan

Research output: Contribution to journalArticle (Academic Journal)peer-review

4 Citations (Scopus)

Abstract

We propose a structured learning approach,max-margin structure (MMS), which is targeted at natural language processing (NLP) tasks. The architecture of our approach is shown to capture structural aspects of the problem domains, leading to demonstrable performance improvements on two NLP tasks: part-of-speech tagging and statistical machine translation (SMT).We present a perceptron-based online learning algorithmto train themodel and demonstrate desirable computational scaling behavior over traditional optimisation methods.
Translated title of the contributionThe application of structured learning in natural language processing
Original languageEnglish
Pages (from-to)71 - 85
Number of pages15
JournalMachine Translation Journal
Volume24
DOIs
Publication statusPublished - May 2010

Bibliographical note

Publisher: Springer

Fingerprint Dive into the research topics of 'The application of structured learning in natural language processing'. Together they form a unique fingerprint.

Cite this