يعالج ملء القالب عموما من قبل خط أنابيب لنظمين تحت إشراف منفصلين - واحدة لاستخراج الدوران وآخر للاعتراف بالقوالب / الحدث.نظرا لأن خطوط الأنابيب تنظر في الأحداث بمعزل، فيمكنها أن تعاني من انتشار الأخطاء.نقدم إطارا يعتمد على المحولات الإندانية الطرفية لهذه المهمة (I.E.، GTT).من الطبيعي طرز الاعتماد بين الكيانات داخل حدث واحد وعبر الأحداث المتعددة الموصوفة في وثيقة.توضح التجارب أن هذا الإطار يتفوق بشكل كبير على الأساليب القائمة على خط الأنابيب، وغيرها من خطوط الأساس شبه إلى النهائي التي لا تضع طراز بين التبعيات بين الحدث.نظهر كذلك أن إطار عملنا يحسن على وجه التحديد الأداء على المستندات التي تحتوي على أحداث متعددة.
Template filling is generally tackled by a pipeline of two separate supervised systems -- one for role-filler extraction and another for template/event recognition. Since pipelines consider events in isolation, they can suffer from error propagation. We introduce a framework based on end-to-end generative transformers for this task (i.e., GTT). It naturally models the dependence between entities both within a single event and across the multiple events described in a document. Experiments demonstrate that this framework substantially outperforms pipeline-based approaches, and other neural end-to-end baselines that do not model between-event dependencies. We further show that our framework specifically improves performance on documents containing multiple events.
References used
https://aclanthology.org/
Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and with a hig
In transfer learning, it is imperative to achieve strong alignment between a pre-trained model and a downstream task. Prior work has done this by proposing task-specific pre-training objectives, which sacrifices the inherent scalability of the transf
Current benchmark tasks for natural language processing contain text that is qualitatively different from the text used in informal day to day digital communication. This discrepancy has led to severe performance degradation of state-of-the-art NLP m
Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic computation and memory requirements with respect to sequence length. Successful approaches to re
Offensive language detection (OLD) has received increasing attention due to its societal impact. Recent work shows that bidirectional transformer based methods obtain impressive performance on OLD. However, such methods usually rely on large-scale we