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

arXiv: https://arxiv.org/abs/2201.04810 · HTML: https://mlsanity.com/paper/2201.04810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 11 of 11)

- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Learning to Compose Task-Specific Tree Structures](https://mlsanity.com/paper/1707.02786/) (2017)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [A Deep Network Model for Paraphrase Detection in Short Text Messages](https://mlsanity.com/paper/1712.02820/) (2017)
- [Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations](https://mlsanity.com/paper/1809.02286/) (2018)
- [Sentence Modeling via Multiple Word Embeddings and Multi-level Comparison for Semantic Textual Similarity](https://mlsanity.com/paper/1805.07882/) (2018)
- [Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning](https://mlsanity.com/paper/1802.03238/) (2018)
- [Learning to Compose over Tree Structures via POS Tags](https://mlsanity.com/paper/1808.06075/) (2018)
- [Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification](https://mlsanity.com/paper/1803.01165/) (2018)
- [An enhanced Tree-LSTM architecture for sentence semantic modeling using typed dependencies](https://mlsanity.com/paper/2002.07775/) (2020)

## Abstract (arXiv)

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.