A brief survey on recent advances in coreference resolution

被引：11
作者：
Liu, Ruicheng [1 ]
Mao, Rui [1 ]
Luu, Anh Tuan [1 ]
Cambria, Erik [1 ]
机构：
[1] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
来源：
ARTIFICIAL INTELLIGENCE REVIEW | 2023年 / 56卷 / 12期
关键词：
Coreference resolution; Natural language processing; Artificial intelligence; Deep learning;
D O I：
10.1007/s10462-023-10506-3
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The task of resolving repeated objects in natural languages is known as coreference resolution, and it is an important part of modern natural language processing. It is classified into two categories depending on the resolved objects, namely entity coreference resolution and event coreference resolution. Predicting coreference connections and identifying mentions/triggers are the major challenges in coreference resolution, because these implicit relationships are particularly difficult in natural language understanding in downstream tasks. Coreference resolution techniques have experienced considerable advances in recent years, encouraging us to review this task in the following aspects: current employed evaluation metrics, datasets, and methods. We investigate 10 widely used metrics, 18 datasets and 4 main technical trends in this survey. We believe that this work is a comprehensive roadmap for understanding the past and the future of coreference resolution.
引用
收藏
页码：14439 / 14481
页数：43
相关论文
共 140 条
  • [1] Abzaliev A, 2019, GENDER BIAS IN NATURAL LANGUAGE PROCESSING (GEBNLP 2019), P107
  • [2] Achiam J., 2023, GPT 4 TECHNICAL REPO
  • [3] Agarwal Oshin., 2019, Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, P1
  • [4] Angeli G, 2015, PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, P344
  • [5] [Anonymous], 2016, P 5 WORKSHOP AUTOMAT
  • [6] Aralikatte R, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P1229
  • [7] Improving opinion retrieval in social media by combining features-based coreferencing and memory-based learning
    Atkinson, John
    Salas, Gonzalo
    Figueroa, Alejandro
    [J]. INFORMATION SCIENCES, 2015, 299 : 20 - 31
  • [8] Attree S, 2019, GENDER BIAS IN NATURAL LANGUAGE PROCESSING (GEBNLP 2019), P134
  • [9] Bagga Amit, 1998, 1 INT C LANG RES EV, V1, P563
  • [10] Bamman D, 2020, PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), P44
12345678910