Some open problems in machine learning for NLP

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Natural language processing is obstructed by two problems: that of ambiguity, and that of skewed distributions. Together they engender acute sparsity of data for supervised learning, both of grammars and parsing models.
The paper expresses some pessimism about the prospects for getting around this problem using unsupervised methods, and considers the prospects for finding naturally labeled datasets to extend supervised methods.
Original languageEnglish
Title of host publication2011 Symposium on Machine Learning in Speech and Language Processing, MLSLP 2011, Bellevue, WA, USA, June 27, 2011
Number of pages1
Publication statusPublished - 2011

Fingerprint

Dive into the research topics of 'Some open problems in machine learning for NLP'. Together they form a unique fingerprint.

Cite this