A brief survey on recent advances in coreference resolution
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 resolu...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170039 |
| _version_ | 1826121959040090112 |
|---|---|
| author | Liu, Ruicheng Mao, Rui Luu, Anh Tuan Cambria, Erik |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Liu, Ruicheng Mao, Rui Luu, Anh Tuan Cambria, Erik |
| author_sort | Liu, Ruicheng |
| collection | NTU |
| description | 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. |
| first_indexed | 2024-10-01T05:40:41Z |
| format | Journal Article |
| id | ntu-10356/170039 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:40:41Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1700392023-08-22T05:54:54Z A brief survey on recent advances in coreference resolution Liu, Ruicheng Mao, Rui Luu, Anh Tuan Cambria, Erik School of Computer Science and Engineering Engineering::Computer science and engineering Coreference Resolution Natural Language Processing 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. Agency for Science, Technology and Research (A*STAR) This study is supported under the RIE2020 Industry Alignment Fund-Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from the industry partner(s). 2023-08-22T05:54:54Z 2023-08-22T05:54:54Z 2023 Journal Article Liu, R., Mao, R., Luu, A. T. & Cambria, E. (2023). A brief survey on recent advances in coreference resolution. Artificial Intelligence Review. https://dx.doi.org/10.1007/s10462-023-10506-3 0269-2821 https://hdl.handle.net/10356/170039 10.1007/s10462-023-10506-3 2-s2.0-85160264426 en Artificial Intelligence Review © 2023 The Author(s), under exclusive licence to Springer Nature B.V. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Coreference Resolution Natural Language Processing Liu, Ruicheng Mao, Rui Luu, Anh Tuan Cambria, Erik A brief survey on recent advances in coreference resolution |
| title | A brief survey on recent advances in coreference resolution |
| title_full | A brief survey on recent advances in coreference resolution |
| title_fullStr | A brief survey on recent advances in coreference resolution |
| title_full_unstemmed | A brief survey on recent advances in coreference resolution |
| title_short | A brief survey on recent advances in coreference resolution |
| title_sort | brief survey on recent advances in coreference resolution |
| topic | Engineering::Computer science and engineering Coreference Resolution Natural Language Processing |
| url | https://hdl.handle.net/10356/170039 |
| work_keys_str_mv | AT liuruicheng abriefsurveyonrecentadvancesincoreferenceresolution AT maorui abriefsurveyonrecentadvancesincoreferenceresolution AT luuanhtuan abriefsurveyonrecentadvancesincoreferenceresolution AT cambriaerik abriefsurveyonrecentadvancesincoreferenceresolution AT liuruicheng briefsurveyonrecentadvancesincoreferenceresolution AT maorui briefsurveyonrecentadvancesincoreferenceresolution AT luuanhtuan briefsurveyonrecentadvancesincoreferenceresolution AT cambriaerik briefsurveyonrecentadvancesincoreferenceresolution |