Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization

• URL: http://arxiv.org/abs/2305.18926v1
• Date: Tue, 30 May 2023 10:33:05 GMT
• Title: Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization
• Authors: Xinyu Wang, Lin Gui, Yulan He
• Abstract summary: Document-level multi-event extraction aims to extract structural information from a given document automatically. We propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. Our model outperforms previous state-of-the-art method in F1-score on two datasets with only a fraction of training time.
• Score: 31.065768513381414
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Document-level multi-event extraction aims to extract the structural information from a given document automatically. Most recent approaches usually involve two steps: (1) modeling entity interactions; (2) decoding entity interactions into events. However, such approaches ignore a global view of inter-dependency of multiple events. Moreover, an event is decoded by iteratively merging its related entities as arguments, which might suffer from error propagation and is computationally inefficient. In this paper, we propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization. The event proxy nodes, representing pseudo-events, are able to build connections with other event proxy nodes, essentially capturing global information. The Hausdorff distance makes it possible to compare the similarity between the set of predicted events and the set of ground-truth events. By directly minimizing Hausdorff distance, the model is trained towards the global optimum directly, which improves performance and reduces training time. Experimental results show that our model outperforms previous state-of-the-art method in F1-score on two datasets with only a fraction of training time.

Related papers

• Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information [33.21818213257603]
  Cross-document event coreference resolution models can only compute mention similarity directly or enhance mention representation by extracting event arguments. We propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. We have developed a large-scale Chinese cross-document event coreference dataset to fill this gap.
  arXiv  Detail & Related papers  (2024-06-23T02:54:48Z)
• Improving Event Definition Following For Zero-Shot Event Detection [66.27883872707523]
  Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types. We aim to improve zero-shot event detection by training models to better follow event definitions.
  arXiv  Detail & Related papers  (2024-03-05T01:46:50Z)
• More than Classification: A Unified Framework for Event Temporal Relation Extraction [61.44799147458621]
  Event temporal relation extraction(ETRE) is usually formulated as a multi-label classification task. We observe that all relations can be interpreted using the start and end time points of events. We propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points.
  arXiv  Detail & Related papers  (2023-05-28T02:09:08Z)
• MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction [78.61546292830081]
  We construct a large-scale human-annotated ERE dataset MAVEN-ERE with improved annotation schemes. It contains 103,193 event coreference chains, 1,216,217 temporal relations, 57,992 causal relations, and 15,841 subevent relations. Experiments show that ERE on MAVEN-ERE is quite challenging, and considering relation interactions with joint learning can improve performances.
  arXiv  Detail & Related papers  (2022-11-14T13:34:49Z)
• RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction [16.87868728956481]
  We propose a new DEE framework which can model the relation dependencies, called Relation-augmented Document-level Event Extraction (ReDEE) To further leverage relation information, we introduce a separate event relation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance.
  arXiv  Detail & Related papers  (2022-06-07T15:11:42Z)
• EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction [52.43978926985928]
  We introduce the Event-Aware Argument Extraction (EA$2$E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$2$E.
  arXiv  Detail & Related papers  (2022-05-30T04:33:51Z)
• PILED: An Identify-and-Localize Framework for Few-Shot Event Detection [79.66042333016478]
  In our study, we employ cloze prompts to elicit event-related knowledge from pretrained language models. We minimize the number of type-specific parameters, enabling our model to quickly adapt to event detection tasks for new types.
  arXiv  Detail & Related papers  (2022-02-15T18:01:39Z)
• Learning Constraints and Descriptive Segmentation for Subevent Detection [74.48201657623218]
  We propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction. We adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model.
  arXiv  Detail & Related papers  (2021-09-13T20:50:37Z)
• Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker [23.990907956996413]
  Document-level event extraction aims to recognize event information from a whole piece of article. Existing methods are not effective due to two challenges of this task. We propose Heterogeneous Graph-based Interaction Model with a Tracker.
  arXiv  Detail & Related papers  (2021-05-31T12:45:03Z)
• Document-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies [37.96254956540803]
  We propose an end-to-end model leveraging Deep Value Networks (DVN), a structured prediction algorithm, to efficiently capture cross-event dependencies for document-level event extraction. Our approach achieves comparable performance to CRF-based models on ACE05, while enjoys significantly higher computational efficiency.
  arXiv  Detail & Related papers  (2020-10-24T05:28:16Z)
• Predicting Event Time by Classifying Sub-Level Temporal Relations Induced from a Unified Representation of Time Anchors [10.67457147373144]
  We propose an effective method to decompose complex temporal relations into sub-level relations. Our approach outperforms the state-of-the-art decision tree model.
  arXiv  Detail & Related papers  (2020-08-14T16:30:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.