UMichigan: a conditional random field model for resolving the scope of negation

Authors:
Amjad Abu-Jbara;Dragomir Radev
Affiliations:
University of Michigan, Ann Arbor, MI;University of Michigan, Ann Arbor, MI
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 8
Cited 0

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Extracting contrastive information from negation patterns in biomedical literature

ACM Transactions on Asian Language Information Processing (TALIP)
Recognizing contextual polarity in phrase-level sentiment analysis

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Learning the scope of hedge cues in biomedical texts

BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
Learning the scope of negation in biomedical texts

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
The effect of negation on sentiment analysis and retrieval effectiveness

Proceedings of the 18th ACM conference on Information and knowledge management
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
A survey on the role of negation in 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

In this paper, we present a system for detecting negation in English text. We address three tasks: negation cue detection, negation scope resolution and negated event identification. We pose these tasks as sequence labeling problems. For each task, we train a Conditional Random Field (CRF) model on lexical, structural, and syntactic features extracted from labeled data. The models are trained and tested using the dataset distributed with the *sem Shared Task 2012 on resolving the scope and focus of negation. The system detects negation cues with 90.98% F1 measure (94.3% and 87.88% recall). It identifies negation scope with 82.70% F1 on token-by-token level and 64.78% F1 on full scope level. Negated events are detected with 51.10% F1 measure.