Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion

• URL: http://arxiv.org/abs/2408.03079v1
• Date: Tue, 6 Aug 2024 10:15:15 GMT
• Title: Enhancing Complex Causality Extraction via Improved Subtask Interaction and Knowledge Fusion
• Authors: Jinglong Gao, Chen Lu, Xiao Ding, Zhongyang Li, Ting Liu, Bing Qin,
• Abstract summary: Event Causality Extraction aims at extracting causal event pairs from texts. Existing fine-tuning based ECE methods cannot address all three key challenges in ECE simultaneously. We propose a unified ECE framework (UniCE) to address all three issues in ECE simultaneously.
• Score: 35.14378353659475
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT's recent success, fine-tuning small models remains the best approach for the ECE task. However, existing fine-tuning based ECE methods cannot address all three key challenges in ECE simultaneously: 1) Complex Causality Extraction, where multiple causal-effect pairs occur within a single sentence; 2) Subtask~ Interaction, which involves modeling the mutual dependence between the two subtasks of ECE, i.e., extracting events and identifying the causal relationship between extracted events; and 3) Knowledge Fusion, which requires effectively fusing the knowledge in two modalities, i.e., the expressive pretrained language models and the structured knowledge graphs. In this paper, we propose a unified ECE framework (UniCE to address all three issues in ECE simultaneously. Specifically, we design a subtask interaction mechanism to enable mutual interaction between the two ECE subtasks. Besides, we design a knowledge fusion mechanism to fuse knowledge in the two modalities. Furthermore, we employ separate decoders for each subtask to facilitate complex causality extraction. Experiments on three benchmark datasets demonstrate that our method achieves state-of-the-art performance and outperforms ChatGPT with a margin of at least 30% F1-score. More importantly, our model can also be used to effectively improve the ECE performance of ChatGPT via in-context learning.

Related papers

• Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering [13.835512118463164]
  Event-Event Causal Relation Extraction (ECRE) aims to identify and classify the causal relationships between event mentions in natural language texts. Existing research on ECRE has highlighted two critical challenges, including the lack of document-level modeling and causal hallucinations. We propose a Knowledge-guided binary Question Answering (KnowQA) method with event structures for ECRE, consisting of two stages: Event Structure Construction and Binary Question Answering.
  arXiv  Detail & Related papers  (2024-10-07T05:07:48Z)
• CARE: Co-Attention Network for Joint Entity and Relation Extraction [0.0]
  We propose a Co-Attention network for joint entity and relation extraction. Our approach includes adopting a parallel encoding strategy to learn separate representations for each subtask. At the core of our approach is the co-attention module that captures two-way interaction between the two subtasks.
  arXiv  Detail & Related papers  (2023-08-24T03:40:54Z)
• Co-evolving Graph Reasoning Network for Emotion-Cause Pair Extraction [39.76268402567324]
  We propose a new MTL framework based on Co-evolving Reasoning. We show that our model achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-06-07T11:11:12Z)
• Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction [36.123715709125015]
  Emotion cause pair extraction (ECPE) is one of the derived subtasks of emotion cause analysis (ECA) ECPE shares rich inter-related features with emotion extraction (EE) and cause extraction (CE)
  arXiv  Detail & Related papers  (2022-09-09T04:06:27Z)
• A Co-Interactive Transformer for Joint Slot Filling and Intent Detection [61.109486326954205]
  Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. Previous studies either model the two tasks separately or only consider the single information flow from intent to slot. We propose a Co-Interactive Transformer to consider the cross-impact between the two tasks simultaneously.
  arXiv  Detail & Related papers  (2020-10-08T10:16:52Z)
• DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification [77.59549450705384]
  In dialog system, dialog act recognition and sentiment classification are two correlative tasks. Most of the existing systems either treat them as separate tasks or just jointly model the two tasks. We propose a Deep Co-Interactive Relation Network (DCR-Net) to explicitly consider the cross-impact and model the interaction between the two tasks.
  arXiv  Detail & Related papers  (2020-08-16T14:13:32Z)
• An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis [73.7488524683061]
  We propose a novel Iterative Multi-Knowledge Transfer Network (IMKTN) for end-to-end ABSA. Our IMKTN transfers the task-specific knowledge from any two of the three subtasks to another one at the token level by utilizing a well-designed routing algorithm. Experimental results on three benchmark datasets demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2020-04-04T13:49:54Z)
• Cascaded Human-Object Interaction Recognition [175.60439054047043]
  We introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. At each stage, an instance localization network progressively refines HOI proposals and feeds them into an interaction recognition network. With our carefully-designed human-centric relation features, these two modules work collaboratively towards effective interaction understanding.
  arXiv  Detail & Related papers  (2020-03-09T17:05:04Z)
• Knowledge Integration Networks for Action Recognition [58.548331848942865]
  We design a three-branch architecture consisting of a main branch for action recognition, and two auxiliary branches for human parsing and scene recognition. We propose a two-level knowledge encoding mechanism which contains a Cross Branch Integration (CBI) module for encoding the auxiliary knowledge into medium-level convolutional features, and an Action Knowledge Graph (AKG) for effectively fusing high-level context information. The proposed KINet achieves the state-of-the-art performance on a large-scale action recognition benchmark Kinetics-400, with a top-1 accuracy of 77.8%.
  arXiv  Detail & Related papers  (2020-02-18T10:20:30Z)

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.