جيل القصة هي مهمة تهدف إلى إنشاء قصة ذات مغزى تلقائيا. هذه المهمة صعبة لأنها تتطلب فهما رفيع المستوى للمعنى الدلالي للجمل والسببية لأحداث القصة. تفشل نماذج NaiveSequence-To-Stuncence عموما في الحصول على هذه المعرفة، حيث يصعب ضمان صحة منطقية في نموذج جيل نصي دون تخطيط استراتيجي. في هذه الدراسة، نركز على التخطيط لسلسلة من الأحداث بمساعدة الرسوم البيانية الحدث واستخدام الأحداث لتوجيه المولد. بدلا من استخدام نموذج تسلسل إلى تسلسل لإخراج تسلسل، كما هو الحال في بعض الأعمال الموجودة، نقترح إنشاء تسلسل حدث من خلال المشي في رسم بياني حدث. يتم بناء الرسوم البيانية للحدث بناء على Corpus. لتقييم النهج المقترح، ندمج المشاركة البشرية، سواء في تخطيط الأحداث وتوليد القصة. استنادا إلى نتائج الشروح البشرية لارجكيستال، فقد ثبت أن نهجنا المقترح تقديم تسلسل وحدث صحيح منطقيا وقصصا مقارنة بالنهج السابقة.
Story generation is a task that aims to automatically generate a meaningful story. This task is challenging because it requires high-level understanding of the semantic meaning of sentences and causality of story events. Naivesequence-to-sequence models generally fail to acquire such knowledge, as it is difficult to guarantee logical correctness in a text generation model without strategic planning. In this study, we focus on planning a sequence of events assisted by event graphs and use the events to guide the generator. Rather than using a sequence-to-sequence model to output a sequence, as in some existing works, we propose to generate an event sequence by walking on an event graph. The event graphs are built automatically based on the corpus. To evaluate the proposed approach, we incorporate human participation, both in event planning and story generation. Based on the largescale human annotation results, our proposed approach has been shown to provide more logically correct event sequences and stories compared with previous approaches.
References used
https://aclanthology.org/
Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. The best human-crafted stories exhibit coherent plot, strong characters, and adherence to genres, attributes that current states-of
Event detection (ED) task aims to classify events by identifying key event trigger words embedded in a piece of text. Previous research have proved the validity of fusing syntactic dependency relations into Graph Convolutional Networks(GCN). While ex
Sentence fusion is a conditional generation task that merges several related sentences into a coherent one, which can be deemed as a summary sentence. The importance of sentence fusion has long been recognized by communities in natural language gener
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating t
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities. In this paper, we emphasize the importance of incorporating events