استخراج الأحداث على مستوى المستند أمر بالغ الأهمية لمختلف مهام معالجة اللغة الطبيعية لتوفير معلومات منظمة.النهج الحالية عن طريق النمذجة المتسلسلة إهمال الهياكل المنطقية المعقدة للنصوص الطويلة.في هذه الورقة، نستفيد بين تفاعلات الكيان وتفاعلات الجملة خلال المستندات الطويلة وتحويل كل وثيقة إلى رسم بياني غير مرمى غير مسبهب من خلال استغلال العلاقة بين الجمل.نقدم مجتمع الجملة لتمثيل كل حدث كشركة فرعية.علاوة على ذلك.توضح التجارب أن إطارنا يحقق نتائج تنافسية على الأساليب الحديثة على مجموعة بيانات استخراج الأحداث على مستوى الوثيقة على نطاق واسع.
Document-level event extraction is critical to various natural language processing tasks for providing structured information. Existing approaches by sequential modeling neglect the complex logic structures for long texts. In this paper, we leverage the entity interactions and sentence interactions within long documents and transform each document into an undirected unweighted graph by exploiting the relationship between sentences. We introduce the Sentence Community to represent each event as a subgraph. Furthermore, our framework SCDEE maintains the ability to extract multiple events by sentence community detection using graph attention networks and alleviate the role overlapping issue by predicting arguments in terms of roles. Experiments demonstrate that our framework achieves competitive results over state-of-the-art methods on the large-scale document-level event extraction dataset.
References used
https://aclanthology.org/
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and entity core
Document-level relation extraction aims to identify relations between entities in a whole document. Prior efforts to capture long-range dependencies have relied heavily on implicitly powerful representations learned through (graph) neural networks, w
Extracting relations across large text spans has been relatively underexplored in NLP, but it is particularly important for high-value domains such as biomedicine, where obtaining high recall of the latest findings is crucial for practical applicatio
We study the problem of Cross-lingual Event Argument Extraction (CEAE). The task aims to predict argument roles of entity mentions for events in text, whose language is different from the language that a predictive model has been trained on. Previous
Document-level relation extraction is a challenging task, requiring reasoning over multiple sentences to predict a set of relations in a document. In this paper, we propose a novel framework E2GRE (Entity and Evidence Guided Relation Extraction) that