A Neural Entity Coreference Resolution Review
arXiv:1910.09329 · doi:10.1016/j.eswa.2020.114466
Abstract
Entity Coreference Resolution is the task of resolving all mentions in a document that refer to the same real world entity and is considered as one of the most difficult tasks in natural language understanding. It is of great importance for downstream natural language processing tasks such as entity linking, machine translation, summarization, chatbots, etc. This work aims to give a detailed review of current progress on solving Coreference Resolution using neural-based approaches. It also provides a detailed appraisal of the datasets and evaluation metrics in the field, as well as the subtask of Pronoun Resolution that has seen various improvements in the recent years. We highlight the advantages and disadvantages of the approaches, the challenges of the task, the lack of agreed-upon standards in the task and propose a way to further expand the boundaries of the field.
arXiv comment52 pages, 8 figures, 4 tables, Published in Expert Systems with Applications
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- Polyglot: Distributed Word Representations for Multilingual NLP
- Adversarial Training Methods for Semi-Supervised Text Classification
- Distral: Robust Multitask Reinforcement Learning
- Word sense disambiguation: a complex network approach
- Classifying informative and imaginative prose using complex networks
- Multi-hop Question Answering via Reasoning Chains
- Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
- Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It
- Context in Neural Machine Translation: A Review of Models and Evaluations
- An Annotated Dataset of Coreference in English Literature
- Learning to Search for Dependencies
- Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns
- Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference
- Syntactic Scaffolds for Semantic Structures
- Rewarding Coreference Resolvers for Being Consistent with World Knowledge
- Entity Candidate Network for Whole-Aware Named Entity Recognition