Recognizing textual entailment: is word similarity enough?

Authors:
Valentin Jijkoun;Maarten de Rijke
Affiliations:
Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands;Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands
Venue:
MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment
Year:
2005

Citing 2
Cited 7

Modern Information Retrieval

Modern Information Retrieval
An Information-Theoretic Definition of Similarity

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning

Bootstrapping distributional feature vector quality

Computational Linguistics
A discourse commitment-based framework for recognizing textual entailment

RTE '07 Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing
Probabilistic tree-edit models with structured latent variables for textual entailment and question answering

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
The automatic identification of lexical variation between language varieties

Natural Language Engineering
Learning to select the correct answer in multi-stream question answering

Information Processing and Management: an International Journal
An approach for textual entailment recognition based on stacking and voting

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
Refining the judgment threshold to improve recognizing textual entailment using similarity

ICCCI'12 Proceedings of the 4th international conference on Computational Collective Intelligence: technologies and applications - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe the system we used at the PASCAL-2005 Recognizing Textual Entailment Challenge. Our method for recognizing entailment is based on calculating “directed” sentence similarity: checking the directed “semantic” word overlap between the text and the hypothesis. We use frequency-based term weighting in combination with two different word similarity measures. Although one version of the system shows significant improvement over randomly guessing decisions (with an accuracy score of 57.3), we show that this is only due to a subset of the data that can be equally well handled by simple word overlap. Furthermore, we give an in-depth analysis of the system and the data of the challenge.