Event Coreference Resolution: A Survey of Two Decades of Research

@inproceedings{Lu2018EventCR,
  title={Event Coreference Resolution: A Survey of Two Decades of Research},
  author={Jing Lu and Vincent Ng},
  booktitle={IJCAI},
  year={2018}
}
Recent years have seen a gradual shift of focus from entity-based tasks to event-based tasks in information extraction research. 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. 

Figures and Tables from this paper

Span-Based Event Coreference Resolution
TLDR
Empirical results on the standard evaluation dataset provide affirmative answers to all three questions about whether the successes of spanbased models of entity coreference can be extended to event coreference.
Event Coreference Resolution with Non-Local Information
We present two extensions to a state-of-theart joint model for event coreference resolution, which involve incorporating (1) a supervised topic model for improving trigger detection by providing
Constrained Multi-Task Learning for Event Coreference Resolution
TLDR
The novel idea of viewing entity coreference and event coreference as a single coreference task is proposed, which is believed to be a step towards a unified model of coreference resolution.
Event Coreference Resolution for Contentious Politics Events
TLDR
It is found that almost half of the event mentions in documents co-occur with other event mentions and this makes it inevitable to obtain erroneous or partial event information, and it is shown that event coreference resolution could help improving this situation.
Precision Event Coreference Resolution Using Neural Network Classifiers
TLDR
This paper presents a neural network classifier approach to detecting precise within-document (WD) and cross- document (CD) event coreference clusters effectively using only event mention based features and uses no sophisticated clustering approach.
End-to-End Neural Event Coreference Resolution
XCoref: Cross-document Coreference Resolution in the Wild
TLDR
Outperforming an established CDCR model shows that the new CDCR models need to be evaluated on semantically complex mentions with more loose coreference relations to indicate their applicability of models to resolve mentions in the “wild” of political news articles.
Event and Entity Coreference using Trees to Encode Uncertainty in Joint Decisions
TLDR
An alternating optimization method for inference that when clustering event mentions, considers the uncertainty of the clustering of entity mentions and vice-versa, and it is shown that the proposed joint model provides empirical advantages over state-of-the-art independent and joint models.
Event Clustering within News Articles
This paper summarizes our group’s efforts in the event sentence coreference identification shared task, which is organized as part of the Automated Extraction of Socio-Political Events from News
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
TLDR
A novel context-dependent gated module to adaptively control the information flows from the input symbolic features and achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.
...
...

References

SHOWING 1-10 OF 64 REFERENCES
A Pairwise Event Coreference Model, Feature Impact and Evaluation for Event Coreference Resolution
TLDR
The problem of event coreference resolution in the ACE program is formally state, an agglomerative clustering algorithm for the task is presented, the feature impact in theevent coreference model is explored, and three evaluation metrics that were previously adopted in entity coreferenceresolution are compared.
Supervised Within-Document Event Coreference using Information Propagation
TLDR
A supervised method for event coreference resolution is presented that uses a rich feature set and propagates information alternatively between events and their arguments, adapting appropriately for each type of argument.
Graph-based Event Coreference Resolution
  • Zheng Chen, Heng Ji
  • Computer Science
    Graph-based Methods for Natural Language Processing
  • 2009
TLDR
This paper models event coreference resolution as a spectral graph clustering problem and evaluates the clustering algorithm on ground truth event mentions using ECM F-Measure and obtains the ECM-F scores of 0.8363 and 0.8312 respectively.
Event coreference for information extraction
We propose a general approach for performing event coreference and for constructing complex event representations, such as those required for information extraction tasks. Our approach is based on a
Learning Antecedent Structures for Event Coreference Resolution
  • Jing Lu, Vincent Ng
  • Computer Science
    2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)
  • 2017
TLDR
This work views event coreference as a structured prediction task, where it proposes a probabilistic model that selects an antecedent for each event mention in a given document in a collective manner.
Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers
TLDR
A generative model is proposed for the under-studied task of Chinese event coreference resolution that rivals its supervised counterparts in performance when evaluated on the ACE 2005 corpus.
Joint Entity and Event Coreference Resolution across Documents
TLDR
A novel coreference resolution system that models entities and events jointly that handles nominal and verbal events as well as entities, and the joint formulation allows information from event coreference to help entity coreference, and vice versa.
SinoCoreferencer: An End-to-End Chinese Event Coreference Resolver
TLDR
The design, implementation, and evaluation of SinoCoreferencer, an end-to-end state-of-the-art ACE-style Chinese event coreference system, is described and made publicly available to facilitate the development of high-level Chinese natural language applications that can potentially benefit fromevent coreference information.
A Unified Event Coreference Resolution by Integrating Multiple Resolvers
TLDR
A globally optimized coreference resolution system dedicated to various sophisticated event coreference phenomena and an efficient and globally optimized graph partitioning model is employed for coreference chain formation using spectral partitioning which allows the incorporation of pronoun coreference information.
Translating Granularity of Event Slots into Features for Event Coreference Resolution
TLDR
In this study, granularity of events is determined and the grain size is used as a clue for solving event coreference and results show that determining granularity along semantic event slots improves precision and solvesevent coreference with scores comparable to those achieved in related work.
...
...