# Relation Classification as Two-way Span-Prediction

arXiv: https://arxiv.org/abs/2010.04829 · HTML: https://mlsanity.com/paper/2010.04829/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [GPT-RE: In-context Learning for Relation Extraction using Large Language Models](https://mlsanity.com/paper/2305.02105/) (2023)
- [Relation Classification with Entity Type Restriction](https://mlsanity.com/paper/2105.08393/) (2021)
- [Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text](https://mlsanity.com/paper/2106.01033/) (2021)
- [Do Models Learn the Directionality of Relations? A New Evaluation: Relation Direction Recognition](https://mlsanity.com/paper/2105.09045/) (2021)
- [CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm](https://mlsanity.com/paper/2210.06246/) (2022)
- [Towards Realistic Few-Shot Relation Extraction: A New Meta Dataset and Evaluation](https://mlsanity.com/paper/2404.04445/) (2024)
- [LabelPrompt: Effective Prompt-based Learning for Relation Classification](https://mlsanity.com/paper/2302.08068/) (2023)
- [About Evaluation of F1 Score for RECENT Relation Extraction System](https://mlsanity.com/paper/2305.09410/) (2023)
- [Zero-Shot Dialogue Relation Extraction by Relating Explainable Triggers and Relation Names](https://mlsanity.com/paper/2306.06141/) (2023)

## Abstract (arXiv)

The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.