Revealing the Myth of Higher-Order Inference in Coreference Resolution

2020/09/25 by Liyan Xu, Jinho D. Choi, Xu, Liyan +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2009.12013

openalex publication_date 2020/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works

Related

• Higher-order Coreference Resolution with Coarse-to-fine Inference
• Improving Coreference Resolution by Learning Entity-Level Distributed\n Representations
• End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline
• A Controlled Reevaluation of Coreference Resolution Models
• Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference