DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying

• URL: http://arxiv.org/abs/2405.13325v2
• Date: Sat, 15 Jun 2024 15:40:49 GMT
• Title: DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying
• Authors: Guanghui Wang, Dexi Liu, Jian-Yun Nie, Qizhi Wan, Rong Hu, Xiping Liu, Wanlong Liu, Jiaming Liu,
• Abstract summary: Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. We propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, and an event-guided adaptive gating mechanism.
• Score: 32.115904077731386
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference, such as retrieved instances and event templates. These methods face two challenges: (1) the retrieval results may be irrelevant and (2) templates are developed independently for each event without considering their possible relationship. In this work, we propose DEGAP to address these challenges through a simple yet effective components: dual prefixes, i.e. learnable prompt vectors, where the instance-oriented prefix and template-oriented prefix are trained to learn information from different event instances and templates. Additionally, we propose an event-guided adaptive gating mechanism, which can adaptively leverage possible connections between different events and thus capture relevant information from the prefix. Finally, these event-guided prefixes provide relevant information as cues to EAE model without retrieval. Extensive experiments demonstrate that our method achieves new state-of-the-art performance on four datasets (ACE05, RAMS, WIKIEVENTS, and MLEE). Further analysis shows the impact of different components.

Related papers

• Grounding Partially-Defined Events in Multimodal Data [61.0063273919745]
  We introduce a multimodal formulation for partially-defined events and cast the extraction of these events as a three-stage span retrieval task. We propose a benchmark for this task, MultiVENT-G, that consists of 14.5 hours of densely annotated current event videos and 1,168 text documents, containing 22.8K labeled event-centric entities. Results illustrate the challenges that abstract event understanding poses and demonstrates promise in event-centric video-language systems.
  arXiv  Detail & Related papers  (2024-10-07T17:59:48Z)
• Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction [19.51890490853855]
  We propose a multiple-event argument extraction model DEEIA. It is capable of extracting arguments from all events within a document simultaneously. Our method achieves new state-of-the-art performance on four public datasets.
  arXiv  Detail & Related papers  (2024-05-03T07:04:35Z)
• GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling [89.07386210297373]
  GenEARL is a training-free generative framework that harnesses the power of modern generative models to understand event task descriptions. We show that GenEARL outperforms the contrastive pretraining (CLIP) baseline by 9.4% and 14.2% accuracy for zero-shot EARL on the M2E2 and SwiG datasets.
  arXiv  Detail & Related papers  (2024-04-07T00:28:13Z)
• From Simple to Complex: A Progressive Framework for Document-level Informative Argument Extraction [34.37013964529546]
  Event Argument Extraction (EAE) requires the model to extract arguments of multiple events from a single document. We propose a simple-to-complex progressive framework for document-level EAE. Our model outperforms SOTA by 1.4% in F1, indicating the proposed simple-to-complex framework is useful in the EAE task.
  arXiv  Detail & Related papers  (2023-10-25T04:38:02Z)
• PESE: Event Structure Extraction using Pointer Network based Encoder-Decoder Architecture [0.0]
  Event extraction (EE) aims to find the events and event-related argument information from the text and represent them in a structured format. In this paper, we represent each event record in a unique format that contains trigger phrase, trigger type, argument phrase, and corresponding role information. Our proposed pointer network-based encoder-decoder model generates an event in each step by exploiting the interactions among event participants.
  arXiv  Detail & Related papers  (2022-11-22T10:36:56Z)
• Dynamic Prefix-Tuning for Generative Template-based Event Extraction [31.581360683375337]
  We propose a generative template-based event extraction method with dynamic prefix (GTEE-DynPref) Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model OneIE on ACE 2005. Our model is proven to be portable to new types of events effectively.
  arXiv  Detail & Related papers  (2022-05-12T15:38:34Z)
• 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)
• Event Data Association via Robust Model Fitting for Event-based Object Tracking [66.05728523166755]
  We propose a novel Event Data Association (called EDA) approach to explicitly address the event association and fusion problem. The proposed EDA seeks for event trajectories that best fit the event data, in order to perform unifying data association and information fusion. The experimental results show the effectiveness of EDA under challenging scenarios, such as high speed, motion blur, and high dynamic range conditions.
  arXiv  Detail & Related papers  (2021-10-25T13:56:00Z)
• Detecting Ongoing Events Using Contextual Word and Sentence Embeddings [110.83289076967895]
  This paper introduces the Ongoing Event Detection (OED) task. The goal is to detect ongoing event mentions only, as opposed to historical, future, hypothetical, or other forms or events that are neither fresh nor current. Any application that needs to extract structured information about ongoing events from unstructured texts can take advantage of an OED system.
  arXiv  Detail & Related papers  (2020-07-02T20:44:05Z)
• Extensively Matching for Few-shot Learning Event Detection [66.31312496170139]
  Event detection models under super-vised learning settings fail to transfer to new event types. Few-shot learning has not beenexplored in event detection. We propose two novelloss factors that matching examples in the sup-port set to provide more training signals to themodel.
  arXiv  Detail & Related papers  (2020-06-17T18:30:30Z)

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.