Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies
This work addresses the problem of distinguishing semantically dissimilar sentences with identical words and syntax for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackled the challenge of recognizing semantic relations in sentence pairs by improving Dependency Tree-RNNs with grammatical relationship types from dependency parses, achieving a 2% accuracy improvement in recognizing textual entailment and higher correlation scores in semantic relatedness tasks.
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.