# Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

arXiv: https://arxiv.org/abs/1903.02591 · HTML: https://mlsanity.com/paper/1903.02591/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2019.

## Built on by (most cited first, 22 of 22)

- [Fully Hyperbolic Neural Networks](https://mlsanity.com/paper/2105.14686/) (2021)
- [Prompt-Learning for Fine-Grained Entity Typing](https://mlsanity.com/paper/2108.10604/) (2021)
- [Ultra-Fine Entity Typing with Weak Supervision from a Masked Language Model](https://mlsanity.com/paper/2106.04098/) (2021)
- [Modeling Fine-Grained Entity Types with Box Embeddings](https://mlsanity.com/paper/2101.00345/) (2021)
- [Fine-grained Entity Typing via Label Reasoning](https://mlsanity.com/paper/2109.05744/) (2021)
- [Unified Semantic Typing with Meaningful Label Inference](https://mlsanity.com/paper/2205.01826/) (2022)
- [Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference](https://mlsanity.com/paper/2202.06167/) (2022)
- [Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing](https://mlsanity.com/paper/2205.12640/) (2022)
- [Automatic Noisy Label Correction for Fine-Grained Entity Typing](https://mlsanity.com/paper/2205.03011/) (2022)
- [Generative Entity Typing with Curriculum Learning](https://mlsanity.com/paper/2210.02914/) (2022)
- [Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Models](https://mlsanity.com/paper/2305.09785/) (2023)
- [Ultra-Fine Entity Typing with Prior Knowledge about Labels: A Simple Clustering Based Strategy](https://mlsanity.com/paper/2305.12802/) (2023)
- [Modeling Label Correlations for Ultra-Fine Entity Typing with Neural Pairwise Conditional Random Field](https://mlsanity.com/paper/2212.01581/) (2022)
- [Recall, Expand and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing](https://mlsanity.com/paper/2212.09125/) (2022)
- [Fine-Grained Chemical Entity Typing with Multimodal Knowledge Representation](https://mlsanity.com/paper/2108.12899/) (2021)
- [Ontology Enrichment for Effective Fine-grained Entity Typing](https://mlsanity.com/paper/2310.07795/) (2023)
- [Dense Retrieval as Indirect Supervision for Large-space Decision Making](https://mlsanity.com/paper/2310.18619/) (2023)
- [Type-enriched Hierarchical Contrastive Strategy for Fine-Grained Entity Typing](https://mlsanity.com/paper/2208.10081/) (2022)
- [Denoising Enhanced Distantly Supervised Ultrafine Entity Typing](https://mlsanity.com/paper/2210.09599/) (2022)
- [Recognizing Unseen States of Unknown Objects by Leveraging Knowledge Graphs](https://mlsanity.com/paper/2307.12179/) (2023)
- [What do Deck Chairs and Sun Hats Have in Common? Uncovering Shared Properties in Large Concept Vocabularies](https://mlsanity.com/paper/2310.14793/) (2023)
- [Modelling Commonsense Commonalities with Multi-Facet Concept Embeddings](https://mlsanity.com/paper/2403.16984/) (2024)

## Abstract (arXiv)

Existing entity typing systems usually exploit the type hierarchy provided by knowledge base (KB) schema to model label correlations and thus improve the overall performance. Such techniques, however, are not directly applicable to more open and practical scenarios where the type set is not restricted by KB schema and includes a vast number of free-form types. To model the underly-ing label correlations without access to manually annotated label structures, we introduce a novel label-relational inductive bias, represented by a graph propagation layer that effectively encodes both global label co-occurrence statistics and word-level similarities.On a large dataset with over 10,000 free-form types, the graph-enhanced model equipped with an attention-based matching module is able to achieve a much higher recall score while maintaining a high-level precision. Specifically, it achieves a 15.3% relative F1 improvement and also less inconsistency in the outputs. We further show that a simple modification of our proposed graph layer can also improve the performance on a conventional and widely-tested dataset that only includes KB-schema types.