# Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition

arXiv: https://arxiv.org/abs/2004.14514 · HTML: https://mlsanity.com/paper/2004.14514/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [SpanNER: Named Entity Re-/Recognition as Span Prediction](https://mlsanity.com/paper/2106.00641/) (2021)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [Named Entity Recognition in Indian court judgments](https://mlsanity.com/paper/2211.03442/) (2022)
- [Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2208.14565/) (2022)
- [Decomposed Meta-Learning for Few-Shot Named Entity Recognition](https://mlsanity.com/paper/2204.05751/) (2022)
- [Interpretability for Language Learners Using Example-Based Grammatical Error Correction](https://mlsanity.com/paper/2203.07085/) (2022)
- [Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning](https://mlsanity.com/paper/2305.13628/) (2023)
- [WojoodNER 2023: The First Arabic Named Entity Recognition Shared Task](https://mlsanity.com/paper/2310.16153/) (2023)
- [Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications](https://mlsanity.com/paper/2310.19942/) (2023)
- [WojoodNER 2024: The Second Arabic Named Entity Recognition Shared Task](https://mlsanity.com/paper/2407.09936/) (2024)
- [Span Classification with Structured Information for Disfluency Detection in Spoken Utterances](https://mlsanity.com/paper/2203.16028/) (2022)
- [Larger-Context Tagging: When and Why Does It Work?](https://mlsanity.com/paper/2104.04434/) (2021)
- [Deep Span Representations for Named Entity Recognition](https://mlsanity.com/paper/2210.04182/) (2022)
- [MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries](https://mlsanity.com/paper/2408.12980/) (2024)
- [Instance-Based Neural Dependency Parsing](https://mlsanity.com/paper/2109.13497/) (2021)
- [DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition](https://mlsanity.com/paper/2211.08104/) (2022)
- [Span-based Named Entity Recognition by Generating and Compressing Information](https://mlsanity.com/paper/2302.05392/) (2023)
- [Win-Win Cooperation: Bundling Sequence and Span Models for Named Entity Recognition](https://mlsanity.com/paper/2207.03300/) (2022)
- [An Empirical Study on Finding Spans](https://mlsanity.com/paper/2210.06824/) (2022)
- [To be Continuous, or to be Discrete, Those are Bits of Questions](https://mlsanity.com/paper/2406.07812/) (2024)
- [Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling](https://mlsanity.com/paper/2307.07946/) (2023)
- [Language Chameleon: Transformation analysis between languages using Cross-lingual Post-training based on Pre-trained language models](https://mlsanity.com/paper/2209.06422/) (2022)
- [CodeNER: Code Prompting for Named Entity Recognition](https://mlsanity.com/paper/2507.20423/) (2025)

## Abstract (arXiv)

Interpretable rationales for model predictions play a critical role in practical applications. In this study, we develop models possessing interpretable inference process for structured prediction. Specifically, we present a method of instance-based learning that learns similarities between spans. At inference time, each span is assigned a class label based on its similar spans in the training set, where it is easy to understand how much each training instance contributes to the predictions. Through empirical analysis on named entity recognition, we demonstrate that our method enables to build models that have high interpretability without sacrificing performance.