EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention

• URL: http://arxiv.org/abs/2210.12463v1
• Date: Sat, 22 Oct 2022 14:51:12 GMT
• Title: EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention
• Authors: Chen Tang, Chenghua Lin, Henglin Huang, Frank Guerin and Zhihao Zhang
• Abstract summary: We present EtriCA, a novel neural generation model, which improves the relevance and coherence of the generated stories. We show that our model significantly outperforms state-of-the-art baselines.
• Score: 17.049035309926637
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One of the key challenges of automatic story generation is how to generate a long narrative that can maintain fluency, relevance, and coherence. Despite recent progress, current story generation systems still face the challenge of how to effectively capture contextual and event features, which has a profound impact on a model's generation performance. To address these challenges, we present EtriCA, a novel neural generation model, which improves the relevance and coherence of the generated stories through residually mapping context features to event sequences with a cross-attention mechanism. Such a feature capturing mechanism allows our model to better exploit the logical relatedness between events when generating stories. Extensive experiments based on both automatic and human evaluations show that our model significantly outperforms state-of-the-art baselines, demonstrating the effectiveness of our model in leveraging context and event features.

Related papers

• A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation [28.046803293933213]
  We introduce a novel neural generation model, EtriCA, that enhances the relevance and coherence of generated stories. We employ a post-training framework for knowledge enhancement (KeEtriCA) on a large-scale book corpus. This results in approximately 5% improvement in automatic metrics and over 10% improvement in human evaluation.
  arXiv  Detail & Related papers  (2023-11-19T08:54:47Z)
• Controllable Topic-Focused Abstractive Summarization [57.8015120583044]
  Controlled abstractive summarization focuses on producing condensed versions of a source article to cover specific aspects. This paper presents a new Transformer-based architecture capable of producing topic-focused summaries.
  arXiv  Detail & Related papers  (2023-11-12T03:51:38Z)
• Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation [59.417443739208146]
  We propose a new event forecasting model based on a novel training framework of historical contrastive learning. CENET learns both the historical and non-historical dependency to distinguish the most potential entities. We evaluate our proposed model on five benchmark graphs.
  arXiv  Detail & Related papers  (2023-08-29T03:26:38Z)
• Automated Action Model Acquisition from Narrative Texts [13.449750550301992]
  We present NaRuto, a system that extracts structured events from narrative text and generates planning-language-style action models. Experimental results in classical narrative planning domains show that NaRuto can generate action models of significantly better quality than existing fully automated methods.
  arXiv  Detail & Related papers  (2023-07-17T07:04:31Z)
• Conditional Generative Modeling for High-dimensional Marked Temporal Point Processes [9.141687745550481]
  We propose a novel event-generation framework for modeling point processes with high-dimensional marks. We use a conditional generator that takes the history of events as input and generates the high-quality subsequent event. Our numerical results demonstrate superior performance compared to other state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-05-21T21:13:10Z)
• NGEP: A Graph-based Event Planning Framework for Story Generation [17.049035309926637]
  We propose NGEP, a novel event planning framework which generates an event sequence by performing inference on an automatically constructed event graph. We conduct a range of experiments on multiple criteria, and the results demonstrate that our graph-based neural framework outperforms the state-of-the-art (SOTA) event planning approaches.
  arXiv  Detail & Related papers  (2022-10-19T14:49:27Z)
• 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)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• Cue Me In: Content-Inducing Approaches to Interactive Story Generation [74.09575609958743]
  We focus on the task of interactive story generation, where the user provides the model mid-level sentence abstractions. We present two content-inducing approaches to effectively incorporate this additional information. Experimental results from both automatic and human evaluations show that these methods produce more topically coherent and personalized stories.
  arXiv  Detail & Related papers  (2020-10-20T00:36:15Z)

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.