# Interpreting Sentiment Composition with Latent Semantic Tree

arXiv: https://arxiv.org/abs/2308.16588 · HTML: https://mlsanity.com/paper/2308.16588/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 58 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Rationalizing Neural Predictions](https://mlsanity.com/paper/1606.04155/) (2016)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Interpretable Neural Predictions with Differentiable Binary Variables](https://mlsanity.com/paper/1905.08160/) (2019)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking](https://mlsanity.com/paper/2004.14992/) (2020)
- [Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection](https://mlsanity.com/paper/2004.02015/) (2020)
- [Learning to Compose Task-Specific Tree Structures](https://mlsanity.com/paper/1707.02786/) (2017)
- [Interpretation of NLP models through input marginalization](https://mlsanity.com/paper/2010.13984/) (2020)
- [Sentiment Analysis Based on Deep Learning: A Comparative Study](https://mlsanity.com/paper/2006.03541/) (2020)
- [Do Human Rationales Improve Machine Explanations?](https://mlsanity.com/paper/1905.13714/) (2019)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [Cooperative Learning of Disjoint Syntax and Semantics](https://mlsanity.com/paper/1902.09393/) (2019)
- [Fine-grained Sentiment Analysis with Faithful Attention](https://mlsanity.com/paper/1908.06870/) (2019)
- [Modeling Hierarchical Structures with Continuous Recursive Neural Networks](https://mlsanity.com/paper/2106.06038/) (2021)
- [Neural CRF Parsing](https://mlsanity.com/paper/1507.03641/) (2015)
- [Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsing](https://mlsanity.com/paper/1806.00840/) (2018)
- [Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations](https://mlsanity.com/paper/1809.02286/) (2018)
- [A Statistical Parsing Framework for Sentiment Classification](https://mlsanity.com/paper/1401.6330/) (2014)
- [Dynamic Compositional Neural Networks over Tree Structure](https://mlsanity.com/paper/1705.04153/) (2017)
- [Latent Variable Sentiment Grammar](https://mlsanity.com/paper/1907.00218/) (2019)
- [Building Interpretable Interaction Trees for Deep NLP Models](https://mlsanity.com/paper/2007.04298/) (2020)

## Abstract (arXiv)

As the key to sentiment analysis, sentiment composition considers the classification of a constituent via classifications of its contained sub-constituents and rules operated on them. Such compositionality has been widely studied previously in the form of hierarchical trees including untagged and sentiment ones, which are intrinsically suboptimal in our view. To address this, we propose semantic tree, a new tree form capable of interpreting the sentiment composition in a principled way. Semantic tree is a derivation of a context-free grammar (CFG) describing the specific composition rules on difference semantic roles, which is designed carefully following previous linguistic conclusions. However, semantic tree is a latent variable since there is no its annotation in regular datasets. Thus, in our method, it is marginalized out via inside algorithm and learned to optimize the classification performance. Quantitative and qualitative results demonstrate that our method not only achieves better or competitive results compared to baselines in the setting of regular and domain adaptation classification, and also generates plausible tree explanations.