Cross-document Coreference Resolution Research Articles

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.

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.

DataSynapse: A Social Data Curation Foundry

Social data analytics have become a vital asset for organizations and governments. For example, over the last few years, governments started to extract knowledge and derive insights from vastly growing open data to personalize the advertisements in elections, improve government services, predict intelligence activities, as well as to improve national security and public health. A key challenge in analyzing social data is to transform the raw data generated by social actors into curated data, i.e., contextualized data and knowledge that is maintained and made available for use by end-users and applications. To address this challenge, we present the notion of knowledge lake, i.e., a contextualized Data Lake, to provide the foundation for big data analytics by automatically curating the raw social data and to prepare them for deriving insights. We present a social data curation foundry, namely DataSynapse, to enable analysts engage with social data to uncover hidden patterns and generate insight. In DataSynapse, we present a scalable algorithm to transform social items (e.g., a Tweet in Twitter) into semantic items, i.e., contextualized and curated items. This algorithm offers customizable feature extraction to harness desired features from diverse data sources. To link contextualized information items to the domain knowledge, we present a scalable technique which leverages cross document coreference resolution assisting analysts to derive targeted insights. DataSynapse is offered as an extensible and scalable microservice-based architecture that are publicly available on GitHub supporting networks such as Twitter, Facebook, GooglePlus and LinkedIn. We adopt a typical scenario for analyzing urban social issues from Twitter as it relates to the government budget, to highlight how DataSynapse significantly improves the quality of extracted knowledge compared to the classical curation pipeline (in the absence of feature extraction, enrichment and domain-linking contextualization).

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 systematic review and comparative analysis of cross-document coreference resolution methods and tools

Information extraction (IE) is the task of automatically extracting structured information from unstructured/semi-structured machine-readable documents. Among various IE tasks, extracting actionable intelligence from an ever-increasing amount of data depends critically upon cross-document coreference resolution (CDCR) - the task of identifying entity mentions across information sources that refer to the same underlying entity. CDCR is the basis of knowledge acquisition and is at the heart of Web search, recommendations, and analytics. Real time processing of CDCR processes is very important and have various applications in discovering must-know information in real-time for clients in finance, public sector, news, and crisis management. Being an emerging area of research and practice, the reported literature on CDCR challenges and solutions is growing fast but is scattered due to the large space, various applications, and large datasets of the order of peta-/tera-bytes. In order to fill this gap, we provide a systematic review of the state of the art of challenges and solutions for a CDCR process. We identify a set of quality attributes, that have been frequently reported in the context of CDCR processes, to be used as a guide to identify important and outstanding issues for further investigations. Finally, we assess existing tools and techniques for CDCR subtasks and provide guidance on selection of tools and algorithms.

Cross-Document Co-Reference Resolution using Sample-Based Clustering with Knowledge Enrichment

Identifying and linking named entities across information sources is the basis of knowledge acquisition and at the heart of Web search, recommendations, and analytics. An important problem in this context is cross-document co-reference resolution (CCR): computing equivalence classes of textual mentions denoting the same entity, within and across documents. Prior methods employ ranking, clustering, or probabilistic graphical models using syntactic features and distant features from knowledge bases. However, these methods exhibit limitations regarding run-time and robustness. This paper presents the CROCS framework for unsupervised CCR, improving the state of the art in two ways. First, we extend the way knowledge bases are harnessed, by constructing a notion of semantic summaries for intra-document co-reference chains using co-occurring entity mentions belonging to different chains. Second, we reduce the computational cost by a new algorithm that embeds sample-based bisection, using spectral clustering or graph partitioning, in a hierarchical clustering process. This allows scaling up CCR to large corpora. Experiments with three datasets show significant gains in output quality, compared to the best prior methods, and the run-time efficiency of CROCS.

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.

Chinese cross document co-reference resolution based on SVM classification and semantics

The task of Cross-Document Co-reference Resolution(CDCR) aims to merge those words distributed in different texts which refer to the same entity together to form co-reference chains.The traditional research on CDCR addresses name disambiguation posed in information retrieval using clustering methods.This paper transformed CDCR as a classification problem by using an Support Vector Machine(SVM) classifier to resolve both name disambiguation and variant consolidation,both of which were prevalent in information extraction.This method can effectively integrate various features,such as morphological,phonetic,and semantic knowledge collected from the corpus and the Internet.The experiment on a Chinese cross-document co-reference corpus shows the classification method outperforms clustering methods in both precision and recall.

A Novel Approach for Cross-Document Coreference Resolution based on Graph Model

A Novel Approach for Cross-Document Coreference Resolution based on Graph Model