Filters








873 Hits in 2.7 sec

End-to-End Neural Event Coreference Resolution [article]

Yaojie Lu and Hongyu Lin and Jialong Tang and Xianpei Han and Le Sun
2020 arXiv   pre-print
In this paper, we propose an End-to-End Event Coreference approach -- E3C neural network, which can jointly model event detection and event coreference resolution tasks, and learn to extract features from  ...  Furthermore, because event mentions are highly diversified and event coreference is intricately governed by long-distance, semantic-dependent decisions, a type-guided event coreference mechanism is further  ...  Improving event coreference resolution by modeling correlations between event coreference chains and document topic structures.  ... 
arXiv:2009.08153v1 fatcat:adytwu7sp5duzmvsifej6mqwt4

Event Coreference Resolution: A Survey of Two Decades of Research

Jing Lu, Vincent Ng
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Being a core event-based task, event coreference resolution is less studied but arguably more challenging than entity coreference resolution.  ...  This paper provides an overview of the major milestones made in event coreference research since its inception two decades ago.  ...  Acknowledgments We thank the two anonymous reviewers for their detailed comments on an earlier draft of the paper. This work was supported in part by NSF Grants IIS-1219142 and IIS-1528037.  ... 
doi:10.24963/ijcai.2018/773 dblp:conf/ijcai/LuN18 fatcat:x4d7nnuhgzbhhfcu6e2dlwln5a

Machine Learning for Entity Coreference Resolution: A Retrospective Look at Two Decades of Research

Vincent Ng
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Though extensively investigated since the 1960s, entity coreference resolution, a core task in natural language understanding, is far from being solved.  ...  Nevertheless, significant progress has been made on learning-based coreference research since its inception two decades ago.  ...  Acknowledgments We thank the three anonymous reviewers for their detailed and insightful comments on an earlier draft of the paper. This work was supported in part by NSF Grant IIS-1219142.  ... 
doi:10.1609/aaai.v31i1.11149 fatcat:g2l4fxdyengk7atxryihiepcki

Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

Chen Chen, Vincent Ng
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
We propose a generative model for the under-studied task of Chinese event coreference resolution that rivals its supervised counterparts in performance when evaluated on the ACE 2005 corpus.  ...  Recent work has successfully leveraged the semantic information extracted from lexical knowledge bases such as WordNet and FrameNet to improve English event coreference resolvers.  ...  Acknowledgments We thank the three anonymous reviewers for their detailed and insightful comments on an earlier draft of this paper.  ... 
doi:10.3115/v1/n15-1116 dblp:conf/naacl/ChenN15 fatcat:nnoyiksourc3jposrx6eneip2q

A set of domain rules and a deep network for protein coreference resolution

Chen Li, Zhiqiang Rao, Qinghua Zheng, Xiangrong Zhang
2018 Database: The Journal of Biological Databases and Curation  
A set of domain rules and a deep network for protein coreference resolution. Abstract Current research of bio-text mining mainly focuses on event extractions.  ...  Bioentity coreference resolution (CR) is a very important method to complete a bio-event's attributes and interconnect events into bio-networks.  ...  CR (Coreference Resolution) breaks sentential boundaries and connects entities from isolated text units, which is useful for both extracting complete bio-events and constructing bio-networks.  ... 
doi:10.1093/database/bay065 pmid:30010737 pmcid:PMC6041745 fatcat:xpx2b4ojmngsbj2mmctnbg6rcm

Joint Learning for Event Coreference Resolution

Jing Lu, Vincent Ng
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
To address this problem, we propose a model for jointly learning event coreference, trigger detection, and event anaphoricity.  ...  To our knowledge, this is the first attempt to train a mention-ranking model and employ event anaphoricity for event coreference.  ...  Acknowledgments We thank the three anonymous reviewers for their detailed comments. This work was supported in part by NSF Grants IIS-1219142 and IIS-1528037.  ... 
doi:10.18653/v1/p17-1009 dblp:conf/acl/LuN17 fatcat:75yrdejmlvdfhjvibjjorsvhru

Entity Coreference Resolution

Vincent Ng
2016 The IEEE intelligent informatics bulletin  
This paper provides an overview of the major milestones made in learning-based coreference research.  ...  Entity coreference resolution is generally considered one of the most difficult tasks in natural language understanding.  ...  MODELS In this section, we examine the major learning-based models for entity coreference resolution. A.  ... 
dblp:journals/cib/Ng16 fatcat:ktbpfzm2evajbipifpb3wzf6wy

A Unified Event Coreference Resolution by Integrating Multiple Resolvers

Bin Chen, Jian Su, Sinno Jialin Pan, Chew Lim Tan
2011 International Joint Conference on Natural Language Processing  
Seven resolvers for both event and object coreference cases are utilized, which include three new resolvers for event coreference resolution.  ...  The three techniques contribute to a significant improvement of 8.54% in B 3 F-score for event coreference resolution on OntoNotes 2.0 corpus.  ...  SVM with Tree-Kernel In such a learning framework, many well-known learning models can be applied to the coreference resolution task.  ... 
dblp:conf/ijcnlp/ChenSPT11 fatcat:r2jzehysjjem3e7h46xrxs5h54

Joint Event Trigger Identification and Event Coreference Resolution with Structured Perceptron

Jun Araki, Teruko Mitamura
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
This paper proposes a document-level structured learning model that simultaneously identifies event triggers and resolves event coreference.  ...  However, traditional approaches addressed event extraction and event coreference resolution either separately or sequentially, which limits their interactions.  ...  Army Research Office (ARO) grant W911NF-14-1-0436 under the Reading, Extraction, and Assembly of Pathways for Evidentiary Reading (REAPER) Program.  ... 
doi:10.18653/v1/d15-1247 dblp:conf/emnlp/ArakiM15 fatcat:albfvdp55vbdzamf3d7uscu2r4

A categorical analysis of coreference resolution errors in biomedical texts

Miji Choi, Justin Zobel, Karin Verspoor
2016 Journal of Biomedical Informatics  
In this study, we perform an investigation of coreference resolution in the biomedical literature.  ...  Through analysis of features of coreference, organised by type of anaphors, we identify that differentiated strategies for each type could be applied to achieve further improvement.  ...  The rulebased approach has been demonstrated to slightly outperform a machine learning approach for coreference resolution related to treatment, test and person (Jonnalagadda et al., 2012) .  ... 
doi:10.1016/j.jbi.2016.02.015 pmid:26925515 fatcat:7n5lwuv34rb6hlkn6nqcwddel4

Overview of BioNLP 2011 Protein Coreference Shared Task

Ngan L. T. Nguyen, Jin-Dong Kim, Jun'ichi Tsujii
2011 Workshop on Biomedical Natural Language Processing  
This paper summarizes the Protein Coreference Resolution task of BioNLP Shared Task 2011. After 7 weeks of system development period, the task received final submissions from 6 teams.  ...  Evaluation results show that state-of-the-art performance on the task can find 22.18% of protein coreferences with the precision of 73.26%.  ...  Among these tools, there is only one team used an external coreference resolution framework, Reconcile, which achieved the state-of-the-art performance for supervised learning-based coreference resolution  ... 
dblp:conf/bionlp/NguyenKT11 fatcat:lcvrrurtizdyzcau3ec3dlbx4e

Abstract Pronominal Anaphora in Three Registers of English
Portland State University

Dominique O'Donnell, Portland State University
2019 McNair Scholars Online Journal  
Non-nominal antecedents are an interesting challenge in coreference resolution because the pronoun provides little information about the syntactic structure or semantics of the antecedent.  ...  A great deal of work in corpus annotation for coreference and coreference resolution has focused on newspaper text and the goal of this study is to investigate how patterns in the use of abstract pronominal  ...  Abstract anaphora with non-nominal antecedents are challenging for coreference resolution for several reasons.  ... 
doi:10.15760/mcnair.2019.13.1.2 fatcat:ucwhva656zdqtlac4cndr5l3ei

Multi-task Learning Based Neural Bridging Reference Resolution [article]

Juntao Yu, Massimo Poesio
2020 arXiv   pre-print
To address this, we use multi-task learning to help bridging reference resolution with coreference resolution.  ...  We propose a multi task learning-based neural model for resolving bridging references tackling two key challenges. The first challenge is the lack of large corpora annotated with bridging references.  ...  By sharing most of the network structure, the mention representations learned by the coreference task become accessible by bridging resolution.  ... 
arXiv:2003.03666v2 fatcat:no6eutmuhjfcpdm4f3yclxdcba

Coreference resolution improves extraction of Biological Expression Language statements from texts

Miji Choi, Haibin Liu, William Baumgartner, Justin Zobel, Karin Verspoor
2016 Database: The Journal of Biological Databases and Curation  
The system incorporates existing text mining components for coreference resolution, biological event extraction and a previously formally untested strategy for BEL statement generation.  ...  We also report that our results evaluated on the training dataset show benefit from integrating coreference resolution with event extraction.  ...  Then, the system identifies events involving identified entities based on a machine learning model for event detection.  ... 
doi:10.1093/database/baw076 pmid:27374122 pmcid:PMC4930833 fatcat:7otkwc3stvcvhcb477zqtzg7ly

Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

Prafulla Kumar Choubey, Ruihong Huang
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
This paper proposes a novel approach for event coreference resolution that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation  ...  structure, and use them with scores obtained from a local coreference relation classifier for jointly resolving multiple event chains in a document.  ...  Joint learning uses a structured conditional random field model that operates at the document level to jointly model event mention extraction, event coreference resolution and an auxiliary task of event  ... 
doi:10.18653/v1/p18-1045 dblp:conf/acl/HuangC18 fatcat:y7ukfqfbubcmhctmtor77l5sve
« Previous Showing results 1 — 15 out of 873 results