EtriCA: Event-triggered context-aware story generation augmented by cross attention
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 …
that can maintain fluency, relevance, and coherence. Despite recent progress, current story …
Improving event representation via simultaneous weakly supervised contrastive learning and clustering
Representations of events described in text are important for various tasks. In this work, we
present SWCC: a Simultaneous Weakly supervised Contrastive learning and Clustering …
present SWCC: a Simultaneous Weakly supervised Contrastive learning and Clustering …
NGEP: A graph-based event planning framework for story generation
To improve the performance of long text generation, recent studies have leveraged
automatically planned event structures (ie storylines) to guide story generation. Such prior …
automatically planned event structures (ie storylines) to guide story generation. Such prior …
[HTML][HTML] A cross-attention augmented model for event-triggered context-aware story generation
Despite recent advancements, existing story generation systems continue to encounter
difficulties in effectively incorporating contextual and event features, which greatly influence …
difficulties in effectively incorporating contextual and event features, which greatly influence …
Fiction-Writing Mode: An Effective Control for Human-Machine Collaborative Writing
W Zhong, J Naradowsky, H Takamura… - Proceedings of the …, 2023 - aclanthology.org
We explore the idea of incorporating concepts from writing skills curricula into human-
machine collaborative writing scenarios, focusing on adding writing modes as a control for …
machine collaborative writing scenarios, focusing on adding writing modes as a control for …
On the Automatic Generation and Simplification of Children's Stories
With recent advances in large language models (LLMs), the concept of automatically
generating children's educational materials has become increasingly realistic. Working …
generating children's educational materials has become increasingly realistic. Working …
LongStory: Coherent, Complete and Length Controlled Long Story Generation
A human author can write any length of story without losing coherence. Also, they always
bring the story to a proper ending, an ability that current language models lack. In this work …
bring the story to a proper ending, an ability that current language models lack. In this work …
Cross-modal contrastive learning for event extraction
S Wang, M Ju, Y Zhang, Y Zheng, M Wang… - … Conference on Database …, 2023 - Springer
Event extraction aims to extract information of triggers and arguments from texts. Recent
advanced methods leverage information from other modalities (eg, images and videos) …
advanced methods leverage information from other modalities (eg, images and videos) …
Comet-m: Reasoning about multiple events in complex sentences
Understanding the speaker's intended meaning often involves drawing commonsense
inferences to reason about what is not stated explicitly. In multi-event sentences, it requires …
inferences to reason about what is not stated explicitly. In multi-event sentences, it requires …
Event representation via contrastive learning with prototype based hard negative sampling
J Kong, Z Yang - Neurocomputing, 2024 - Elsevier
Event representing methods usually use external knowledge to construct potentially more
useful positive or negative samples, while neglecting the importance of sampling them …
useful positive or negative samples, while neglecting the importance of sampling them …