mlsanityData to 14 Oct 2026

Interpreting Sentiment Composition with Latent Semantic Tree

arXiv 2308.16588 ↗First posted 31 Aug 2023cs.CLcited by 0

Not on the map. Why?

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.

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

27 of 58 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 306
  6. 2016Rationalizing Neural Predictionscited by 281
  7. 2016Understanding Neural Networks through Representation Erasurecited by 224
  8. 2018Constituency Parsing with a Self-Attentive Encodercited by 199
  9. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  10. 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
  11. 2020How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Maskingcited by 63
  12. 2020Generating Hierarchical Explanations on Text Classification via Feature Interaction Detectioncited by 57
15 more
  1. 2017Learning to Compose Task-Specific Tree Structurescited by 48
  2. 2020Interpretation of NLP models through input marginalizationcited by 44
  3. 2020Sentiment Analysis Based on Deep Learning: A Comparative Studycited by 37
  4. 2019Do Human Rationales Improve Machine Explanations?cited by 33
  5. 2016Learning to Compose Words into Sentences with Reinforcement Learningcited by 30
  6. 2019Cooperative Learning of Disjoint Syntax and Semanticscited by 27
  7. 2019Fine-grained Sentiment Analysis with Faithful Attentioncited by 23
  8. 2021Modeling Hierarchical Structures with Continuous Recursive Neural Networkscited by 15
  9. 2015Neural CRF Parsingcited by 10
  10. 2018Latent Tree Learning with Differentiable Parsers: Shift-Reduce Parsing and Chart Parsingcited by 7
  11. 2018Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representationscited by 6
  12. 2014A Statistical Parsing Framework for Sentiment Classificationcited by 5
  13. 2017Dynamic Compositional Neural Networks over Tree Structurecited by 3
  14. 2019Latent Variable Sentiment Grammarcited by 1
  15. 2020Building Interpretable Interaction Trees for Deep NLP Modelscited by 1

Built on by

Not cited yet.