# Revealing the Myth of Higher-Order Inference in Coreference Resolution

arXiv: https://arxiv.org/abs/2009.12013 · HTML: https://mlsanity.com/paper/2009.12013/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 30 of 49)

- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Word-Level Coreference Resolution](https://mlsanity.com/paper/2109.04127/) (2021)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [MABEL: Attenuating Gender Bias using Textual Entailment Data](https://mlsanity.com/paper/2210.14975/) (2022)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution](https://mlsanity.com/paper/2205.12644/) (2022)
- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://mlsanity.com/paper/2209.04280/) (2022)
- [LOME: Large Ontology Multilingual Extraction](https://mlsanity.com/paper/2101.12175/) (2021)
- [BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis](https://mlsanity.com/paper/2304.10996/) (2023)
- [Multilingual Coreference Resolution with Harmonized Annotations](https://mlsanity.com/paper/2107.12088/) (2021)
- [Sequential Cross-Document Coreference Resolution](https://mlsanity.com/paper/2104.08413/) (2021)
- [How Gender Debiasing Affects Internal Model Representations, and Why It Matters](https://mlsanity.com/paper/2204.06827/) (2022)
- [Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions](https://mlsanity.com/paper/2402.13551/) (2024)
- [Seq2seq is All You Need for Coreference Resolution](https://mlsanity.com/paper/2310.13774/) (2023)
- ['UFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolution](https://mlsanity.com/paper/2209.07278/) (2022)
- [End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline](https://mlsanity.com/paper/2107.01700/) (2021)
- [Graph Refinement for Coreference Resolution](https://mlsanity.com/paper/2203.16574/) (2022)
- [Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution](https://mlsanity.com/paper/2108.13530/) (2021)
- [Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialogues](https://mlsanity.com/paper/2109.00185/) (2021)
- [Transformers as Graph-to-Graph Models](https://mlsanity.com/paper/2310.17936/) (2023)
- [Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy](https://mlsanity.com/paper/2402.12821/) (2024)
- [SIG: Speaker Identification in Literature via Prompt-Based Generation](https://mlsanity.com/paper/2312.14590/) (2023)
- [A Controlled Reevaluation of Coreference Resolution Models](https://mlsanity.com/paper/2404.00727/) (2024)
- [The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works](https://mlsanity.com/paper/2510.15594/) (2025)
- [A Structured Span Selector](https://mlsanity.com/paper/2205.03977/) (2022)
- [Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD](https://mlsanity.com/paper/2408.16893/) (2024)
- [ELIT: Emory Language and Information Toolkit](https://mlsanity.com/paper/2109.03903/) (2021)
- [Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction](https://mlsanity.com/paper/2205.01909/) (2022)
- [Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations](https://mlsanity.com/paper/2205.10670/) (2022)

## Abstract (arXiv)

This paper analyzes the impact of higher-order inference (HOI) on the task of coreference resolution. HOI has been adapted by almost all recent coreference resolution models without taking much investigation on its true effectiveness over representation learning. To make a comprehensive analysis, we implement an end-to-end coreference system as well as four HOI approaches, attended antecedent, entity equalization, span clustering, and cluster merging, where the latter two are our original methods. We find that given a high-performing encoder such as SpanBERT, the impact of HOI is negative to marginal, providing a new perspective of HOI to this task. Our best model using cluster merging shows the Avg-F1 of 80.2 on the CoNLL 2012 shared task dataset in English.