Event Coreference Resolution based on Convolutional Siamese network and Circle Loss

Dai, Beiya; Qian, Jiang; Cheng, Shiqing; Qiao, Linbo; Li, Dongsheng

doi:10.1109/ijcnn55064.2022.9891886

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Fang et al [20] designed a multi-layer CNN to extract event features, obtained deep semantic information, and further improved the performance of the coreference resolution algorithm by using multiple attention mechanisms. Dai et al [21] enhanced the representation of event text features using a Siamese network framework and used the Circle Loss loss function to maximize intra-class event similarity and minimize inter-class event similarity. Liu et al [22] trained a support vector machine (SVM) classifier based on more than 100 event features to determine whether the events refer to the same entity.…”

Section: Related Workmentioning

confidence: 99%

Short Text Event Coreference Resolution Based on Context Prediction

Yong,

Zeng,

Dai

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Event coreference resolution is the task of clustering event mentions that refer to the same entity or situation in text and performing operations like linking, information completion, and validation. Existing methods model this task as a text similarity problem, focusing solely on semantic information, neglecting key features like event trigger words and subject. In this paper, we introduce the event coreference resolution based on context prediction (ECR-CP) as an alternative to traditional methods. ECR-CP treats the task as sentence-level relationship prediction, examining if two event descriptions can create a continuous sentence-level connection to identify coreference. We enhance ECR-CP with a fusion coding model (ECR-CP+) to incorporate event-specific structure and semantics. The model identifies key text information such as trigger words, argument roles, event types, and tenses via an event extraction module, integrating them into the encoding process as auxiliary features. Extensive experiments on the benchmark CCKS 2021 dataset demonstrate that ECR-CP and ECR-CP+ outperform existing methods in terms of precision, recall, and F1 Score, indicating their superior performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Short Text Event Coreference Resolution Based on Context Prediction

Yong,

Zeng,

Dai

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Most existing works build the scorer on neural networks [15]. In addition to common MLP scorer with Binary Cross Entropy (BCE) loss, Siamese network with circle loss is applied and achieves fair performance [20]. Clustering-oriented regularization terms are also used in the loss function in the training process [21].…”

Section: Event Coreference Resolutionmentioning

confidence: 99%

Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning

Li,

Lu,

Liang

2023

AEHSSR

View full text Add to dashboard Cite

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.

show abstract

Event Coreference Resolution based on Convolutional Siamese network and Circle Loss

Cited by 2 publications

References 13 publications

Short Text Event Coreference Resolution Based on Context Prediction

Short Text Event Coreference Resolution Based on Context Prediction

Pairwise Cross-Document Event Coreference Resolution with Contrastive Learning

Contact Info

Product

Resources

About