# Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction

arXiv: https://arxiv.org/abs/2004.08134 · HTML: https://mlsanity.com/paper/2004.08134/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

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

- [Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality](https://mlsanity.com/paper/2211.00768/) (2022)
- [BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation](https://mlsanity.com/paper/2109.06850/) (2021)
- [HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2202.13352/) (2022)
- [Confidence estimation of classification based on the distribution of the neural network output layer](https://mlsanity.com/paper/2210.07745/) (2022)
- [RuSentEval: Linguistic Source, Encoder Force!](https://mlsanity.com/paper/2103.00573/) (2021)
- [What can Neural Referential Form Selectors Learn?](https://mlsanity.com/paper/2108.06806/) (2021)
- [Getting BART to Ride the Idiomatic Train: Learning to Represent Idiomatic Expressions](https://mlsanity.com/paper/2207.03679/) (2022)
- [Do Charge Prediction Models Learn Legal Theory?](https://mlsanity.com/paper/2210.17108/) (2022)
- [Making Document-Level Information Extraction Right for the Right Reasons](https://mlsanity.com/paper/2110.07686/) (2021)
- [Visualizing the Relationship Between Encoded Linguistic Information and Task Performance](https://mlsanity.com/paper/2203.15860/) (2022)
- [Probing Representations for Document-level Event Extraction](https://mlsanity.com/paper/2310.15316/) (2023)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [Improving Span Representation for Domain-adapted Coreference Resolution](https://mlsanity.com/paper/2109.09811/) (2021)
- [From Consensus to Disagreement: Multi-Teacher Distillation for Semi-Supervised Relation Extraction](https://mlsanity.com/paper/2112.01048/) (2021)
- [Maximizing Relation Extraction Potential: A Data-Centric Study to Unveil Challenges and Opportunities](https://mlsanity.com/paper/2409.04934/) (2024)
- [Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning](https://mlsanity.com/paper/2411.02864/) (2024)
- [Relational Probing: LM-to-Graph Adaptation for Financial Prediction](https://mlsanity.com/paper/2604.10212/) (2026)
- [Lightweight Person-Place Relation Extraction from Historical Newspapers with Dependency Graphs and Proximity Features](https://mlsanity.com/paper/2607.19718/) (2026)

## Abstract (arXiv)

Despite the recent progress, little is known about the features captured by state-of-the-art neural relation extraction (RE) models. Common methods encode the source sentence, conditioned on the entity mentions, before classifying the relation. However, the complexity of the task makes it difficult to understand how encoder architecture and supporting linguistic knowledge affect the features learned by the encoder. We introduce 14 probing tasks targeting linguistic properties relevant to RE, and we use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets, TACRED and SemEval 2010 Task 8. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance. For example, adding contextualized word representations greatly increases performance on probing tasks with a focus on named entity and part-of-speech information, and yields better results in RE. In contrast, entity masking improves RE, but considerably lowers performance on entity type related probing tasks.