Unsupervised detection of downward-entailing operators by maximizing classification certainty

Authors:
Jackie Ck Cheung;Gerald Penn
Affiliations:
University of Toronto Toronto, ON, Canada;University of Toronto Toronto, ON, Canada
Venue:
EACL '12 Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics
Year:
2012

Citing 5
Cited 0

One sense per discourse

HLT '91 Proceedings of the workshop on Speech and Natural Language
Modeling semantic containment and exclusion in natural language inference

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Without a 'doubt'?: unsupervised discovery of downward-entailing operators

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Don't 'have a clue'?: unsupervised co-learning of downward-entailing operators

ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
What's great and what's not: learning to classify the scope of negation for improved sentiment analysis

NeSp-NLP '10 Proceedings of the Workshop on Negation and Speculation in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an unsupervised, iterative method for detecting downward-entailing operators (DEOs), which are important for deducing entailment relations between sentences. Like the distillation algorithm of Danescu-Niculescu-Mizil et al. (2009), the initialization of our method depends on the correlation between DEOs and negative polarity items (NPIs). However, our method trusts the initialization more and aggressively separates likely DEOs from spurious distractors and other words, unlike distillation, which we show to be equivalent to one iteration of EM prior re-estimation. Our method is also am enable to a bootstrapping method that co-learns DEOs and NPIs, and achieves the best results in identifying DEOs in two corpora.