Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization

@inproceedings{KenyonDean2018ResolvingEC,
  title={Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization},
  author={Kian Kenyon-Dean and Jackie Chi Kit Cheung and Doina Precup},
  booktitle={*SEMEVAL},
  year={2018}
}
We present an approach to event coreference resolution by developing a general framework for clustering that uses supervised representation learning. We propose a neural network architecture with novel Clustering-Oriented Regularization (CORE) terms in the objective function. These terms encourage the model to create embeddings of event mentions that are amenable to clustering. We then use agglomerative clustering on these embeddings to build event coreference chains. For both within- and cross… Expand
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. Expand
Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution
  • Hieu Minh Tran, Duy Phung, Thien Huu Nguyen
  • Computer Science
  • ACL/IJCNLP
  • 2021
TLDR
This work introduces a novel deep learning model for ECR that introduces novel regularization techniques based on consistencies of golden and predicted clusters for event mentions in documents and achieves state-of-the-art performance on two benchmark datasets. Expand
Sequential Cross-Document Coreference Resolution
TLDR
A new model is proposed that extends the efficient sequential prediction paradigm for coreference resolution to cross- document settings and achieves competitive results for both entity and event coreference while provides strong evidence of the efficacy of both sequential models and higher-order inference in cross-document settings. Expand
Within-Document Event Coreference with BERT-Based Contextualized Representations
TLDR
This paper presents a three part approach that uses representations derived from a pretrained BERT model to train a neural classifier to drive a simple clustering algorithm to create coreference chains, and establishes a new standard for a newer dataset producing using the Event Hopper approach. Expand
End-to-End Neural Event Coreference Resolution
TLDR
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 raw text automatically, is proposed. Expand
Automatic Data Acquisition for Event Coreference Resolution
TLDR
It is found that a model trained on the authors' acquired event pairs performs comparably as the supervised model when applied to new data out of the training data domains. Expand
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution
TLDR
This work jointly model entity and event coreference, and proposes a neural architecture for cross-document coreference resolution using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures. Expand
Cross-document Coreference Resolution over Predicted Mentions
TLDR
This work introduces the first end-to-end model for CD coreference resolution from raw text, which extends the prominent model for withindocument coreference to the CD setting and achieves competitive results for event and entity coreferenceresolution on gold mentions. Expand
Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference
TLDR
This work model the entities/events in a reader’s focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown. Expand
SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts
TLDR
This work presents a new task of hierarchical CDCR for concepts in scientific papers, with the goal of jointly inferring coreference clusters and hierarchy between them and creates SCICO, an expert-annotated dataset for this task. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 35 REFERENCES
Improving Coreference Resolution by Learning Entity-Level Distributed Representations
TLDR
A neural network based coreference system that produces high-dimensional vector representations for pairs of coreference clusters that learns when combining clusters is desirable and substantially outperforms the current state of the art on the English and Chinese portions of the CoNLL 2012 Shared Task dataset. Expand
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. Expand
Event Linking with Sentential Features from Convolutional Neural Networks
TLDR
This work proposes a model for coreference resolution for event mentions which utilizes sentential features coming from convolutional neural networks, and achieves state-of-the-art performance on two datasets, one of which is publicly available. Expand
A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution
TLDR
A novel hierarchical distance-dependent Bayesian model for event coreference resolution that allows for the incorporation of pairwise distances between event mentions to guide the generative clustering processing for better event clustering both within and across documents. Expand
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. Expand
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. Expand
Unsupervised Event Coreference Resolution
TLDR
A new class of unsupervised, nonparametric Bayesian models with the purpose of probabilistically inferring coreference clusters of event mentions from a collection of unlabeled documents is described, which combines an infinite latent class model with a discrete time series model. Expand
Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events
We introduce a novel iterative approach for event coreference resolution that gradually builds event clusters by exploiting inter-dependencies among event mentions within the same chain as well asExpand
Revisiting the Evaluation for Cross Document Event Coreference
TLDR
A new evaluation methodology is suggested which overcomes limitations of past works, and allows for an accurate assessment of CDEC systems, and better reflects the corpus-wide information aggregation ability ofCDEC systems. Expand
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. Expand
...
1
2
3
4
...