Cross-document Event Coreference Research Articles

Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning

Cross-Document (CD) Event Coreference Resolution (ECR) is a fundamental task in Natural Language processing (NLP) and Knowledge Base Population (KBP). Resolving the event coreference relationship is a challenging task, which necessitates a thorough semantic comprehension of the events. Existing methods have spontaneously formulated this problem as a binary classification task based on sentence segments. However, the information distributed in the longer context is ignored by most prior works. Recent event coreference works focus on adding auxiliary information to improve the performance. The information such as involved entity information, structural information or database queried information is extracted from related documents as long context. Whereas extraction error, matching error and other types of error are introduced in the process of obtaining related information when the context is incomplete. In this work, we present a Contrastive Learning based Pairwise Event Coreference (CLPEC) framework to complete and optimize the CD-ECR task utilizing contextual information with contrastive learning technology. We also adopt augmentation technology to preprocess event representations and improve our performance. Experiment results show that we achieve competitive results on a number of key metrics on the ECB+ corpus.

A Benchmark for Dutch End-to-End Cross-Document Event Coreference Resolution

In this paper, we present a benchmark result for end-to-end cross-document event coreference resolution in Dutch. First, the state of the art of this task in other languages is introduced, as well as currently existing resources and commonly used evaluation metrics. We then build on recently published work to fully explore end-to-end event coreference resolution for the first time in the Dutch language domain. For this purpose, two well-performing transformer-based algorithms for the respective detection and coreference resolution of Dutch textual events are combined in a pipeline architecture and compared to baseline scores relying on feature-based methods. The results are promising and comparable to similar studies in higher-resourced languages; however, they also reveal that in this specific NLP domain, much work remains to be done. In order to gain more insights, an in-depth analysis of the two pipeline components is carried out to highlight and overcome possible shortcoming of the current approach and provide suggestions for future work.

Constructing a cross-document event coreference corpus for Dutch

Event coreference resolution is a task in which different text fragments that refer to the same real-world event are automatically linked together. This task can be performed not only within a single document but also across different documents and can serve as a basis for many useful Natural Language Processing applications. Resources for this type of research, however, are extremely limited. We compiled the first large-scale dataset for cross-document event coreference resolution in Dutch, comparable in size to the most widely used English event coreference corpora. As data for event coreference is notoriously sparse, we took additional steps to maximize the number of coreference links in our corpus. Due to the complex nature of event coreference resolution, many algorithms consist of pipeline architectures which rely on a series of upstream tasks such as event detection, event argument identification and argument coreference. We tackle the task of event argument coreference to both illustrate the potential of our compiled corpus and to lay the groundwork for a Dutch event coreference resolution system in the future. Results show that existing NLP algorithms can be easily retrofitted to contribute to the subtasks of an event coreference resolution pipeline system.

Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora

Cross-document event coreference resolution (CDCR) is an NLP task in which mentions of events need to be identified and clustered throughout a collection of documents. CDCR aims to benefit downstream multidocument applications, but despite recent progress on corpora and system development, downstream improvements from applying CDCR have not been shown yet. We make the observation that every CDCR system to date was developed, trained, and tested only on a single respective corpus. This raises strong concerns on their generalizability—a must-have for downstream applications where the magnitude of domains or event mentions is likely to exceed those found in a curated corpus. To investigate this assumption, we define a uniform evaluation setup involving three CDCR corpora: ECB+, the Gun Violence Corpus, and the Football Coreference Corpus (which we reannotate on token level to make our analysis possible). We compare a corpus-independent, feature-based system against a recent neural system developed for ECB+. Although being inferior in absolute numbers, the feature-based system shows more consistent performance across all corpora whereas the neural system is hit-or-miss. Via model introspection, we find that the importance of event actions, event time, and so forth, for resolving coreference in practice varies greatly between the corpora. Additional analysis shows that several systems overfit on the structure of the ECB+ corpus. We conclude with recommendations on how to achieve generally applicable CDCR systems in the future—the most important being that evaluation on multiple CDCR corpora is strongly necessary. To facilitate future research, we release our dataset, annotation guidelines, and system implementation to the public.1

Precision Event Coreference Resolution Using Neural Network Classifiers

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. Our approach does not rely on any event argument features such as semantic roles or spatio-temporal arguments and uses no sophisticated clustering approach. Experimental results on the ECB+dataset show that our simple approach out performsstate-of-the-art methods for both within-document and cross-document event coreference resolution while producing clusters of high precision, which is useful for several downstream tasks.

Precision Event Coreference Resolution Using Neural Network Classifiers

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. Our approach does not rely on any event argument features such as semantic roles or spatio-temporal arguments and uses no sophisticated clustering approach. Experimental results on the ECB+dataset show that our simple approach out performsstate-of-the-art methods for both within-document and cross-document event coreference resolution while producing clusters of high precision, which is useful for several downstream tasks.

Cross-document event ordering through temporal, lexical and distributional knowledge

In this paper we present a system that automatically builds ordered timelines of events from different written texts in English. The system deals with problems such as automatic event extraction, cross-document temporal relation extraction and cross-document event coreference resolution. Its main characteristic is the application of three different types of knowledge: temporal knowledge, lexical-semantic knowledge and distributional-semantic knowledge, in order to anchor and order the events in the timeline. It has been evaluated within the framework of SemEval 2015. The proposed system improves the current state-of-the-art systems in all measures (up to eight points of F1-score over other systems) and shows a significant advance in the Cross-document event ordering task.

A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolution

We present a novel hierarchical distance-dependent Bayesian model for event coreference resolution. While existing generative models for event coreference resolution are completely unsupervised, our model allows for the incorporation of pairwise distances between event mentions — information that is widely used in supervised coreference models to guide the generative clustering processing for better event clustering both within and across documents. We model the distances between event mentions using a feature-rich learnable distance function and encode them as Bayesian priors for nonparametric clustering. Experiments on the ECB+ corpus show that our model outperforms state-of-the-art methods for both within- and cross-document event coreference resolution.

Unsupervised Event Coreference Resolution

The task of event coreference resolution plays a critical role in many natural language processing applications such as information extraction, question answering, and topic detection and tracking. In this article, we describe 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. In order to infer these clusters, we automatically extract various lexical, syntactic, and semantic features for each event mention from the document collection. Extracting a rich set of features for each event mention allows us to cast event coreference resolution as the task of grouping together the mentions that share the same features (they have the same participating entities, share the same location, happen at the same time, etc.). Some of the most important challenges posed by the resolution of event coreference in an unsupervised way stem from (a) the choice of representing event mentions through a rich set of features and (b) the ability of modeling events described both within the same document and across multiple documents. Our first unsupervised model that addresses these challenges is a generalization of the hierarchical Dirichlet process. This new extension presents the hierarchical Dirichlet process's ability to capture the uncertainty regarding the number of clustering components and, additionally, takes into account any finite number of features associated with each event mention. Furthermore, to overcome some of the limitations of this extension, we devised a new hybrid model, which combines an infinite latent class model with a discrete time series model. The main advantage of this hybrid model stands in its capability to automatically infer the number of features associated with each event mention from data and, at the same time, to perform an automatic selection of the most informative features for the task of event coreference. The evaluation performed for solving both within- and cross-document event coreference shows significant improvements of these models when compared against two baselines for this task.