# Learning from Explanations with Neural Execution Tree

arXiv: https://arxiv.org/abs/1911.01352 · HTML: https://mlsanity.com/paper/1911.01352/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2019.

## Built on by (most cited first, 18 of 18)

- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data](https://mlsanity.com/paper/2102.02201/) (2021)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [Large Language Model Instruction Following: A Survey of Progresses and Challenges](https://mlsanity.com/paper/2303.10475/) (2023)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction](https://mlsanity.com/paper/2101.10213/) (2021)
- [Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment](https://mlsanity.com/paper/2204.03025/) (2022)
- [A survey on improving NLP models with human explanations](https://mlsanity.com/paper/2204.08892/) (2022)
- [CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations](https://mlsanity.com/paper/2204.07142/) (2022)
- [On Evaluating Explanation Utility for Human-AI Decision Making in NLP](https://mlsanity.com/paper/2407.03545/) (2024)
- [Zero-Shot Classification by Logical Reasoning on Natural Language Explanations](https://mlsanity.com/paper/2211.03252/) (2022)
- [Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers](https://mlsanity.com/paper/2311.07538/) (2023)
- [AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction](https://mlsanity.com/paper/2109.04726/) (2021)
- [PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure](https://mlsanity.com/paper/2404.13645/) (2024)
- [Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers](https://mlsanity.com/paper/2101.07138/) (2021)
- [Exploring Automatically Perturbed Natural Language Explanations in Relation Extraction](https://mlsanity.com/paper/2305.15520/) (2023)

## Abstract (arXiv)

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural language (NL) explanations have been demonstrated very useful additional supervision, which can provide sufficient domain knowledge for generating more labeled data over new instances, while the annotation time only doubles. However, directly applying them for augmenting model learning encounters two challenges: (1) NL explanations are unstructured and inherently compositional, which asks for a modularized model to represent their semantics, (2) NL explanations often have large numbers of linguistic variants, resulting in low recall and limited generalization ability. In this paper, we propose a novel Neural Execution Tree (NExT) framework to augment training data for text classification using NL explanations. After transforming NL explanations into executable logical forms by semantic parsing, NExT generalizes different types of actions specified by the logical forms for labeling data instances, which substantially increases the coverage of each NL explanation. Experiments on two NLP tasks (relation extraction and sentiment analysis) demonstrate its superiority over baseline methods. Its extension to multi-hop question answering achieves performance gain with light annotation effort.