يتطلب فهم النص السردي التقاط الدوافع والأهداف والدول الذهنية.تقترح هذه الورقة رسم بياني سرد قائم على الكيان (ENG) لنموذج الدول الداخلية من الشخصيات في القصة.نحن النموذج الصريح كيانات، وتفاعلاتهم والسياق الذي تظهر فيه، وتعلموا تمثيلات غنية لهم.نقوم بتجربة أهداف مختلفة من المهام المتكيفة مسبقا، والتدريب داخل المجال، والاستدلال الرمزي لالتقاط التبعيات بين القرارات المختلفة في مساحة الإنتاج.نقوم بتقييم نموذجنا على مهام فهم سردية: التنبؤ بالحالات العقلية للشخصية، والوفاء بالرغبة، وإجراء تحليل نوعي.
Understanding narrative text requires capturing characters' motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal- states of characters in a story. We explicitly model entities, their interactions and the context in which they appear, and learn rich representations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different decisions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis.
References used
https://aclanthology.org/
In cross-lingual text classification, it is required that task-specific training data in high-resource source languages are available, where the task is identical to that of a low-resource target language. However, collecting such training data can b
Providing a reliable explanation for clinical diagnosis based on the Electronic Medical Record (EMR) is fundamental to the application of Artificial Intelligence in the medical field. Current methods mostly treat the EMR as a text sequence and provid
This paper presents the first study on using large-scale pre-trained language models for automated generation of an event-level temporal graph for a document. Despite the huge success of neural pre-training methods in NLP tasks, its potential for tem
Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relationa
Dominant sentence ordering models can be classified into pairwise ordering models and set-to-sequence models. However, there is little attempt to combine these two types of models, which inituitively possess complementary advantages. In this paper, w