# Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations

arXiv: https://arxiv.org/abs/1809.02286 · HTML: https://mlsanity.com/paper/1809.02286/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2018.

## Built on by (most cited first, 6 of 6)

- [Deep Learning-based Sentiment Classification: A Comparative Survey](https://mlsanity.com/paper/2312.17253/) (2023)
- [Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models](https://mlsanity.com/paper/2211.00479/) (2022)
- [Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies](https://mlsanity.com/paper/2201.04810/) (2022)
- [Interpreting Sentiment Composition with Latent Semantic Tree](https://mlsanity.com/paper/2308.16588/) (2023)
- [Entity-Aware Biaffine Attention Model for Improved Constituent Parsing with Reduced Entity Violations](https://mlsanity.com/paper/2409.00625/) (2024)
- [Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork](https://mlsanity.com/paper/2610.16547/) (2026)

## Abstract (arXiv)

Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We present a novel RvNN architecture that can provide dynamic compositionality by considering comprehensive syntactic information derived from both the structure and linguistic tags. Specifically, we introduce a structure-aware tag representation constructed by a separate tag-level tree-LSTM. With this, we can control the composition function of the existing word-level tree-LSTM by augmenting the representation as a supplementary input to the gate functions of the tree-LSTM. In extensive experiments, we show that models built upon the proposed architecture obtain superior or competitive performance on several sentence-level tasks such as sentiment analysis and natural language inference when compared against previous tree-structured models and other sophisticated neural models.