Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies

TL;DR

This paper enhances Tree-RNN models for sentence pair semantic relation recognition by incorporating grammatical relationship types, leading to improved accuracy and correlation with human judgments.

Contribution

It introduces a novel dependency Tree-RNN variant that uses grammatical relationship types to better capture semantic dissimilarities in sentence pairs.

Findings

2% accuracy improvement in RTE classification

Higher correlation with human similarity ratings

Effective modeling of semantic relationships

Abstract

Recursive neural networks (Tree-RNNs) based on dependency trees are ubiquitous in modeling sentence meanings as they effectively capture semantic relationships between non-neighborhood words. However, recognizing semantically dissimilar sentences with the same words and syntax is still a challenge to Tree-RNNs. This work proposes an improvement to Dependency Tree-RNN (DT-RNN) using the grammatical relationship type identified in the dependency parse. Our experiments on semantic relatedness scoring (SRS) and recognizing textual entailment (RTE) in sentence pairs using SICK (Sentence Involving Compositional Knowledge) dataset show encouraging results. The model achieved a 2% improvement in classification accuracy for the RTE task over the DT-RNN model. The results show that Pearson's and Spearman's correlation measures between the model's predicted similarity scores and human ratings are higher than those of standard DT-RNNs.