Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph

• URL: http://arxiv.org/abs/2112.06013v1
• Date: Sat, 11 Dec 2021 16:01:29 GMT
• Title: Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph
• Authors: Tong Zhu, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Min Zhang
• Abstract summary: We design a non-autoregressive decoding algorithm to perform event argument combination extraction on pruned complete graphs. Compared to the previous systems, our system achieves lower resource consumption, taking only 3.6% GPU time (pfs-days) for training and up to 8.5 times faster for inference.
• Score: 15.925704154438638
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There are two main challenges in document-level event extraction: 1) argument entities are scattered in different sentences, and 2) event triggers are often not available. To address these challenges, most previous studies mainly focus on building argument chains in an autoregressive way, which is inefficient in both training and inference. In contrast to the previous studies, we propose a fast and lightweight model named as PTPCG. We design a non-autoregressive decoding algorithm to perform event argument combination extraction on pruned complete graphs, which are constructed under the guidance of the automatically selected pseudo triggers. Compared to the previous systems, our system achieves competitive results with lower resource consumption, taking only 3.6% GPU time (pfs-days) for training and up to 8.5 times faster for inference. Besides, our approach shows superior compatibility for the datasets with (or without) triggers and the pseudo triggers can be the supplements for annotated triggers to make further improvements.

Related papers

• Instance-Aware Graph Prompt Learning [71.26108600288308]
  We introduce Instance-Aware Graph Prompt Learning (IA-GPL) in this paper. The process involves generating intermediate prompts for each instance using a lightweight architecture. Experiments conducted on multiple datasets and settings showcase the superior performance of IA-GPL compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-11-26T18:38:38Z)
• Are Triggers Needed for Document-Level Event Extraction? [16.944314894087075]
  We provide the first investigation of the role of triggers for the more difficult and much less studied task of document-level event extraction. We analyze their usefulness in multiple end-to-end and pipelined neural event extraction models for three document-level event extraction datasets. Our research shows that trigger effectiveness varies based on the extraction task's characteristics and data quality, with basic, automatically-generated triggers serving as a viable alternative to human-annotated ones.
  arXiv  Detail & Related papers  (2024-11-13T15:50:38Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance [12.239459451494872]
  Document-level event argument extraction poses new challenges of long input and cross-sentence inference. We propose a Span-trigger-based Contextual Pooling and latent Role Guidance model.
  arXiv  Detail & Related papers  (2023-10-08T11:29:10Z)
• Single-Stage Visual Relationship Learning using Conditional Queries [60.90880759475021]
  TraCQ is a new formulation for scene graph generation that avoids the multi-task learning problem and the entity pair distribution. We employ a DETR-based encoder-decoder conditional queries to significantly reduce the entity label space as well. Experimental results show that TraCQ not only outperforms existing single-stage scene graph generation methods, it also beats many state-of-the-art two-stage methods on the Visual Genome dataset.
  arXiv  Detail & Related papers  (2023-06-09T06:02:01Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Retrieval-Augmented Generative Question Answering for Event Argument Extraction [66.24622127143044]
  We propose a retrieval-augmented generative QA model (R-GQA) for event argument extraction. It retrieves the most similar QA pair and augments it as prompt to the current example's context, then decodes the arguments as answers. Our approach outperforms substantially prior methods across various settings.
  arXiv  Detail & Related papers  (2022-11-14T02:00:32Z)
• CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction [22.746071199667146]
  Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document. We propose a Curriculum learning based Prompt tuning (CUP) approach, which resolves implicit EAE by four learning stages. In addition, we integrate a prompt-based encoder-decoder model to elicit related knowledge from pre-trained language models.
  arXiv  Detail & Related papers  (2022-05-01T16:03:54Z)
• Generating Disentangled Arguments with Prompts: A Simple Event Extraction Framework that Works [9.36117752274482]
  Event Extraction bridges the gap between text and event signals. We introduce the prompt-based learning strategy to the domain of Event Extraction. In terms of F1 score on Argument Extraction, our simple architecture is stronger than any other generative counterpart.
  arXiv  Detail & Related papers  (2021-10-09T09:36:08Z)
• Accelerating BERT Inference for Sequence Labeling via Early-Exit [65.7292767360083]
  We extend the recent successful early-exit mechanism to accelerate the inference of PTMs for sequence labeling tasks. We also propose a token-level early-exit mechanism that allows partial tokens to exit early at different layers. Our approach can save up to 66%-75% inference cost with minimal performance degradation.
  arXiv  Detail & Related papers  (2021-05-28T14:39:26Z)
• On Improving Deep Learning Trace Analysis with System Call Arguments [1.3299507495084417]
  Kernel traces are sequences of low-level events comprising a name and multiple arguments. We introduce a general approach to learning a representation of the event names along with their arguments using both embedding and encoding.
  arXiv  Detail & Related papers  (2021-03-11T19:26:34Z)

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.