A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework

• URL: http://arxiv.org/abs/2608.23261v1
• Date: Mon, 24 Aug 2026 13:51:03 GMT
• Title: A Scalable Cross-Domain Event Extraction System via a Unified Generative Training Framework
• Abstract summary: We propose a unified generative sequence-to-sequence framework that performs event extraction subtasks jointly.<n>We fine-tune pretrained language models on multiple event datasets across diverse domains.<n>We demonstrate these capabilities through a web-based application tailored for researchers and practitioners.
• Score: 3.816538153840492
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-specific designs, limiting scalability and cross-domain generalization. We propose a unified generative sequence-to-sequence framework that performs event extraction subtasks jointly and supports both pipeline and end-to-end configurations. We fine-tune pretrained language models on multiple event datasets across diverse domains, enabling a single model to retain domain-specific semantics while generalizing over large and evolving label spaces. We demonstrate these capabilities through a web-based application tailored for researchers and practitioners. The platform supports document upload, schema-aware event extraction, visualization of triggers and arguments, and comparison of different extraction configurations across domains.

Related papers

• A Multi-Domain and Multi-Task Generative Framework with Explicit Task and Domain Conditioning for Cross-Domain Event Extraction [4.169293754839175]
  Event extraction aims to identify event triggers, classify event types, and extract arguments to construct structured event representations.<n>We propose a unified multi-domain and multi-task training framework that models heterogeneous event schemas within a single model.
  arXiv  Detail & Related papers  (2026-08-24T13:24:24Z)
• Unified Video Dense Prediction from Disjoint Data [71.9957801898161]
  We introduce UniD, a unified video model that jointly predicts eight dense scene properties-depth, surface normals, semantic segmentation, boundaries, human parts, albedo, shading, and materials.<n>We propose a simple yet effective distillation step in which per-task experts supervise a unified backbone through lightweight task projectors.<n>UniD achieves competitive performance against per-task specialists and multi-task baselines.
  arXiv  Detail & Related papers  (2026-07-23T17:59:50Z)
• Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning [64.30639042094548]
  We propose a new setting to train a unified cross-domain model through a single process.<n>We first introduce Pose-in-Context (PiC), which leverages in-context learning to create a pose-centric cross-domain model.<n>We thus propose Human-in-Context (HiC), an extension of PiC that broadens generalization across modalities, tasks, and datasets.
  arXiv  Detail & Related papers  (2025-08-14T17:59:23Z)
• PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models [80.65273820998875]
  We present PanMatch, a versatile foundation model for robust correspondence matching.<n>Our key insight is that any two-frame correspondence matching task can be addressed within a 2D displacement estimation framework.<n>PanMatch achieves multi-task integration by endowing displacement estimation algorithms with unprecedented generalization capabilities.
  arXiv  Detail & Related papers  (2025-07-11T08:18:52Z)
• Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction [15.177664715250046]
  We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models. We construct a multi-source, multi-domain corpus and train an end-to-end extraction pipeline. Our results suggest that multi-source training leads to the best overall results, while single-source training yields the best results for the respective individual domain.
  arXiv  Detail & Related papers  (2023-08-05T20:33:39Z)
• Token-Event-Role Structure-based Multi-Channel Document-Level Event Extraction [15.02043375212839]
  This paper introduces a novel framework for document-level event extraction, incorporating a new data structure called token-event-role. The proposed data structure enables our model to uncover the primary role of tokens in multiple events, facilitating a more comprehensive understanding of event relationships. The results demonstrate that our approach outperforms the state-of-the-art method by 9.5 percentage points in terms of the F1 score.
  arXiv  Detail & Related papers  (2023-06-30T15:22:57Z)
• Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding [51.57864297948228]
  We propose a novel event extraction framework that takes event types and argument roles as natural language queries. Our framework benefits from the attention mechanisms to better capture the semantic correlation between the event types or argument roles and the input text.
  arXiv  Detail & Related papers  (2021-10-14T15:49:40Z)
• X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [51.81533991497547]
  Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries. We present X2 compared a transferable Cross-lingual and Cross-domain for TCSP. We propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems.
  arXiv  Detail & Related papers  (2021-06-07T16:40:05Z)
• WikiAsp: A Dataset for Multi-domain Aspect-based Summarization [69.13865812754058]
  We propose WikiAsp, a large-scale dataset for multi-domain aspect-based summarization. Specifically, we build the dataset using Wikipedia articles from 20 different domains, using the section titles and boundaries of each article as a proxy for aspect annotation. Results highlight key challenges that existing summarization models face in this setting, such as proper pronoun handling of quoted sources and consistent explanation of time-sensitive events.
  arXiv  Detail & Related papers  (2020-11-16T10:02:52Z)

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.