Event Causality Is Key to Computational Story Understanding

• URL: http://arxiv.org/abs/2311.09648v2
• Date: Tue, 2 Apr 2024 02:31:59 GMT
• Title: Event Causality Is Key to Computational Story Understanding
• Authors: Yidan Sun, Qin Chao, Boyang Li,
• Abstract summary: We present the first method for event causality identification that leads to material improvements in computational story understanding. In the downstream story quality evaluation task, the identified causal relations lead to 3.6-16.6% relative improvement on correlation with human ratings. The findings indicate substantial untapped potential for event causality in computational story understanding.
• Score: 5.167262076146664
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cognitive science and symbolic AI research suggest that event causality provides vital information for story understanding. However, machine learning systems for story understanding rarely employ event causality, partially due to the lack of methods that reliably identify open-world causal event relations. Leveraging recent progress in large language models, we present the first method for event causality identification that leads to material improvements in computational story understanding. Our technique sets a new state of the art on the COPES dataset (Wang et al., 2023) for causal event relation identification. Further, in the downstream story quality evaluation task, the identified causal relations lead to 3.6-16.6% relative improvement on correlation with human ratings. In the multimodal story video-text alignment task, we attain 4.1-10.9% increase on Clip Accuracy and 4.2-13.5% increase on Sentence IoU. The findings indicate substantial untapped potential for event causality in computational story understanding. The codebase is at https://github.com/insundaycathy/Event-Causality-Extraction.

Related papers

• Event Causality Identification with Synthetic Control [48.18257618831177]
  Event causality identification (ECI) is crucial for distinguishing causation from correlation.<n>Traditional approaches to ECI have primarily utilized linguistic patterns and multi-hop relational inference.<n>In this paper, we adopt the Rubin Causal Model to identify event causality.
  arXiv  Detail & Related papers  (2025-09-16T22:05:52Z)
• Enhancing Event Causality Identification with Rationale and Structure-Aware Causal Question Answering [30.000134835133522]
  Event Causality Identification (DECI) aims to identify causal relations between two events in documents. Recent research tends to use pre-trained language models to generate the event causal relations. We propose a multi-task learning framework to enhance event causality identification with rationale and structure-aware causal question answering.
  arXiv  Detail & Related papers  (2024-03-17T07:41:58Z)
• CLEVRER-Humans: Describing Physical and Causal Events the Human Way [55.44915246065028]
  We present the CLEVRER-Humans benchmark, a video dataset for causal judgment of physical events with human labels. We employ two techniques to improve data collection efficiency: first, a novel iterative event cloze task to elicit a new representation of events in videos, which we term Causal Event Graphs (CEGs); second, a data augmentation technique based on neural language generative models.
  arXiv  Detail & Related papers  (2023-10-05T16:09:48Z)
• Are All Steps Equally Important? Benchmarking Essentiality Detection of Events [92.92425231146433]
  This paper examines the extent to which current models comprehend the essentiality of step events in relation to a goal event. We contribute a high-quality corpus of (goal, step) pairs gathered from the community guideline website WikiHow. The high inter-annotator agreement demonstrates that humans possess a consistent understanding of event essentiality.
  arXiv  Detail & Related papers  (2022-10-08T18:00:22Z)
• ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification [24.894074201193927]
  Event-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. We propose a novel Graph TransfOrmer (ERGO) framework for DECI.
  arXiv  Detail & Related papers  (2022-04-15T12:12:16Z)
• ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification [74.6318379374801]
  We propose to pre-train a general Correlation-aware context-to-Event Transformer (ClarET) for event-centric reasoning. The proposed ClarET is applicable to a wide range of event-centric reasoning scenarios.
  arXiv  Detail & Related papers  (2022-03-04T10:11:15Z)
• Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement [17.77752074834281]
  We propose CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. We adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model.
  arXiv  Detail & Related papers  (2021-06-03T07:50:50Z)
• LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification [17.77752074834281]
  We introduce a new approach to augment training data for event causality identification. Our approach is knowledge-guided, which can leverage existing knowledge bases to generate well-formed new sentences. On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework and can interactively adjust the generation process to generate task-related sentences.
  arXiv  Detail & Related papers  (2021-06-03T07:42:20Z)
• ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning [49.795767003586235]
  We introduce ESTER, a comprehensive machine reading comprehension dataset for Event Semantic Relation Reasoning. We study five most commonly used event semantic relations and formulate them as question answering tasks. Experimental results show that the current SOTA systems achieve 60.5%, 57.8%, and 76.3% for event-based F1, token based F1 and HIT@1 scores respectively.
  arXiv  Detail & Related papers  (2021-04-16T19:59:26Z)
• Learning Contextual Causality from Time-consecutive Images [84.26437953699444]
  Causality knowledge is crucial for many artificial intelligence systems. In this paper, we investigate the possibility of learning contextual causality from the visual signal. We first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that it is possible to automatically discover meaningful causal knowledge from the videos.
  arXiv  Detail & Related papers  (2020-12-13T20:24:48Z)
• Temporal Reasoning on Implicit Events from Distant Supervision [91.20159064951487]
  We propose a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events. We find that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. We propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from large-scale text and uses temporal rules to infer end times.
  arXiv  Detail & Related papers  (2020-10-24T03:12:27Z)

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.