يعد تحليل الإطار الدلالي مهمة تحليل دلالية تعتمد على Framenet التي تلقت اهتماما كبيرا مؤخرا.تتضمن المهمة عادة ثلاث مجموعات فرعية بالتتابع: (1) التعرف المستهدف، (2) تصنيف الإطار و (3) وصف الدور الدليمي.ترتبط المهارات الفرعية الثلاثة ارتباطا وثيقا أثناء وجود دراسات سابقة طرازها بشكل فردي، مما يتجاهل اتصالاتهم المتدربين، وفي الوقت نفسه يحث مشكلة نشر الأخطاء.في هذا العمل، نقترح نموذج عصبي نهاية إلى نهائي لمعالجة المهمة بشكل مشترك.بشكل ملموس، استغلنا طريقة قائمة على الرسم البياني، فيما يتعلق بتحليل الإطار الدلالي كمشكلة بناء الرسم البياني.يتم التعامل مع جميع المسندات والأدوار كجزء رسم بياني، ويتم أخذ علاقاتهم كحواف رسم بياني.نتائج التجربة على مجموعة بيانات قياسية من الإطار الدلالي تظهر أن طريقتنا تنافسية للغاية، مما يؤدي إلى أداء أفضل من نماذج خطوط الأنابيب.
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labeling. The three subtasks are closely related while previous studies model them individually, which ignores their intern connections and meanwhile induces error propagation problem. In this work, we propose an end-to-end neural model to tackle the task jointly. Concretely, we exploit a graph-based method, regarding frame semantic parsing as a graph construction problem. All predicates and roles are treated as graph nodes, and their relations are taken as graph edges. Experiment results on two benchmark datasets of frame semantic parsing show that our method is highly competitive, resulting in better performance than pipeline models.
References used
https://aclanthology.org/
In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Exp
Most previous studies on information status (IS) classification and bridging anaphora recognition assume that the gold mention or syntactic tree information is given (Hou et al., 2013; Roesiger et al., 2018; Hou, 2020; Yu and Poesio, 2020). In this p
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of t
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks