Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures
Published 1 January 2018Open access
Prafulla Kumar Choubey, Ruihong Huang
Citations29
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper explicitly model correlations between the main event chains of a document with topic transition sentences, inter-coreference chain correlations, event mention distributional characteristics and sub-event structure, and use them with scores obtained from a local coreference relation classifier for jointly resolving multiple event chains in a document.
Abstract
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. We explicitly model correlations between the main event chains of a document with topic transition sentences, inter-coreference chain correlations, event mention distributional characteristics and sub-event structure, and use them with scores obtained from a local coreference relation classifier for jointly resolving multiple event chains in a document. Our experiments across KBP 2016 and 2017 datasets suggest that each of the structures contribute to improving event coreference resolution performance.
Keywords
Computer Science
arXiv (Cornell University)Scikit-learn: Machine Learning in Python
63,264 Citations2012Fabián Pedregosa, Gaël Varoquaux +17 more
Glove: Global Vectors for Word Representation
33,769 Citations2014Jeffrey Pennington, Richard Socher +1 more
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
The Stanford CoreNLP Natural Language Processing Toolkit
7,238 Citations2014Christopher D. Manning, Mihai Surdeanu +4 more
The design and use of the Stanford CoreNLP toolkit is described, an extensible pipeline that provides core natural language analysis, and it is suggested that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
Centering: A Framework for Modelling the Local Coherence of Discourse,
1,785 Citations1995Barbara J. Grosz, Aravind K. Joshi +1 more
Interactions between local coherence and choice of referring expressions are examined; it is argued that differences in coherence correspond in part to the inference demands made by different types of referring expressions, given a particular attentional state.
A model-theoretic coreference scoring scheme
682 Citations1995Marc Vilain, John D. Burger +3 more
This note describes a scoring scheme for the coreference task in MUC6 that improves on the original approach by grounding the scoring scheme in terms of a model; producing more intuitive recall and precision scores; and not requiring explicit computation of the transitive closure of coreference.
On coreference resolution performance metrics
535 Citations2005Xiaoqiang Luo
The paper proposes a Constrained Entity-Alignment F-Measure (CEAF) for evaluating coreference resolution and shows that the best alignment is a maximum bipartite matching problem which can be solved by the Kuhn-Munkres algorithm.
The stages of event extraction
511 Citations2006David Ahn
This paper presents a simple, modular approach to event extraction that allows for experiment with a variety of machine learning methods for sub-tasks of varying difficulty, as well as to evaluate the impact on performance these sub-Tasks have on the overall task.
Computational LinguisticsDeterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules
395 Citations2013Heeyoung Lee, Anne Lynn S. Chang +4 more
The two stages of the sieve-based architecture, a mention detection stage that heavily favors recall, followed by coreference sieves that are precision-oriented, offer a powerful way to achieve both high precision and high recall.
Transactions of the Association for Computational LinguisticsA Latent Variable Model Approach to PMI-based Word Embeddings
296 Citations2016Sanjeev Arora, Yuanzhi Li +3 more
A new generative model is proposed, a dynamic version of the log-linear topic model of Mnih and Hinton (2007) to use the prior to compute closed form expressions for word statistics, and it is shown that latent word vectors are fairly uniformly dispersed in space.
Natural Language EngineeringBLANC: Implementing the Rand index for coreference evaluation
200 Citations2010Marc Recasens, Eduard Hovy
The BiLateral Assessment of Noun-Phrase Coreference rewards both coreference and non-coreference links by averaging the F-scores of the two types, and does not ignore singletons – the main problem with the MUC score – and does not inflate the score in their presence.
Joint Entity and Event Coreference Resolution across Documents
186 Citations2012Heeyoung Lee, Marta Vilar Recasens +3 more
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.
INRIA a CCSD electronic archive serverJoint Determination of Anaphoricity and Coreference Resolution using Integer Programming
154 Citations2007Pascal Denis, Jason Baldridge
This paper proposes an integer linear programming (ILP) formulation for coreference resolution which models anaphoricity and coreference as a joint task, such that each local model informs the other for the final assignments.
Unsupervised Event Coreference Resolution with Rich Linguistic Features
154 Citations2010Cosmin A. Bejan, Sanda M. Harabagiu
A new class of nonparametric Bayesian models designed with the purpose of clustering complex linguistic objects can be effectively applied to an open-domain event coreference task.
From Light to Rich ERE: Annotation of Entities, Relations, and Events
141 Citations2015Zhiyi Song, Ann Bies +8 more
The transition from Light ERE to a more complex Rich ERE specification, enabling more comprehensive treatment of phenomena of interest to DEFT is discussed.
Meeting of the Association for Computational LinguisticsUnsupervised Coreference Resolution in a Nonparametric Bayesian Model
135 Citations2007Aria Haghighi, Dan Klein
An unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within each document is presented.
Graph-based event coreference resolution
108 Citations2009Zheng Chen, Heng Ji
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.
Enforcing transitivity in coreference resolution
86 Citations2008Jenny Rose Finkel, Christopher D. Manning
This work trains a coreference classifier over pairs of mentions, and shows how to encode this type of constraint on top of the probabilities output from the pairwise classifier to extract the most probable legal entity assignments.
Transactions of the Association for Computational LinguisticsLatent Structures for Coreference Resolution
79 Citations2015Sebastian Martschat, Michael Strube
A unified representation of different approaches to coreference resolution in terms of the structure they operate on is proposed and a systematic analysis of the output of these approaches is conducted, highlighting differences and similarities.
Computational LinguisticsUnsupervised Event Coreference Resolution
64 Citations2013Cosmin A. Bejan, Sanda M. Harabagiu
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.
Transactions of the Association for Computational LinguisticsA Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution
63 Citations2015Bishan Yang, Claire Cardie +1 more
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.
Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events
62 Citations2017Prafulla Kumar Choubey, Ruihong Huang
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 as across event chains is introduced.
A Pairwise Event Coreference Model, Feature Impact and Evaluation for Event Coreference Resolution
60 Citations2009Zheng Chen, Heng Ji +1 more
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
59 Citations2014Zhengzhong Liu, Jun Araki +2 more
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.
Joint Learning for Event Coreference Resolution
53 Citations2017Jing Lü, Vincent Ng
This is the first attempt to train a mention-ranking model and employ event anaphoricity for event coreference, and achieves the best results to date on the KBP 2016 English and Chinese datasets.
Translating Granularity of Event Slots into Features for Event Coreference Resolution.
53 Citations2015Agata Cybulska, Piek Vossen
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.
Detecting Subevent Structure for Event Coreference Resolution
41 Citations2014Jun Araki, Zhengzhong Liu +2 more
A novel two-stage approach to finding and improving subevent structures by introducing a multiclass logistic regression model that can detect subevent relations in addition to full coreference and proposing a method to improve subevent structure based on subevent clusters detected by the model.
Lexical Features in Coreference Resolution: To be Used With Caution
33 Citations2017Nafise Sadat Moosavi, Michael Strube
It is shown that if coreference resolvers mainly rely on lexical features, they can hardly generalize to unseen domains, and the current coreference resolution evaluation is clearly flawed by only evaluating on a specific split of a specific dataset.
International Conference on Computational LinguisticsJoint Inference for Event Coreference Resolution.
28 Citations2016Jing Lü, Deepak Venugopal +2 more
This work proposes a novel solution where rich features are implicitly encoded into the model by augmenting the MLN distribution with low dimensional unit clauses, and achieves state-of-the-art results on two standard evaluation corpora.
Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations
27 Citations2018Prafulla Kumar Choubey, K.Upendra Raju +1 more
This work observed that the central event of a document usually has many coreferential event mentions that are scattered throughout the document for enabling a smooth transition of subtopics and found that thecentral event can be more accurately identified by further considering the number of sub-events as well as the realis status of an event.
Extracting Subevents via an Effective Two-phase Approach
10 Citations2016Allison Badgett, Ruihong Huang
Evaluation shows the automatically learned subevents help to discover 10% additional main events and improve event detection performance.