# Lightly-supervised Representation Learning with Global Interpretability

arXiv: https://arxiv.org/abs/1805.11545 · HTML: https://mlsanity.com/paper/1805.11545/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2018.

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

- [Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2207.06236/) (2022)
- [Automatic Context Pattern Generation for Entity Set Expansion](https://mlsanity.com/paper/2207.08087/) (2022)
- [MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities](https://mlsanity.com/paper/2307.14878/) (2023)
- [Explaining the Road Not Taken](https://mlsanity.com/paper/2103.14973/) (2021)
- [Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion](https://mlsanity.com/paper/2109.12082/) (2021)
- [From Retrieval to Generation: Efficient and Effective Entity Set Expansion](https://mlsanity.com/paper/2304.03531/) (2023)

## Abstract (arXiv)

We propose a lightly-supervised approach for information extraction, in particular named entity classification, which combines the benefits of traditional bootstrapping, i.e., use of limited annotations and interpretability of extraction patterns, with the robust learning approaches proposed in representation learning. Our algorithm iteratively learns custom embeddings for both the multi-word entities to be extracted and the patterns that match them from a few example entities per category. We demonstrate that this representation-based approach outperforms three other state-of-the-art bootstrapping approaches on two datasets: CoNLL-2003 and OntoNotes. Additionally, using these embeddings, our approach outputs a globally-interpretable model consisting of a decision list, by ranking patterns based on their proximity to the average entity embedding in a given class. We show that this interpretable model performs close to our complete bootstrapping model, proving that representation learning can be used to produce interpretable models with small loss in performance.