تم عرض التعلم النشط للحد من متطلبات التوضيحية للعديد من مهام معالجة اللغة الطبيعية، بما في ذلك وضع العلامات الدلالية (SRL).تنطوي SRL على وسيطة وسيطة تمتد من أجل المحتمل أن يحتمل أن يتسرب المتعددة في جملة، مما يجعل من الصعب تجميع القرارات العديدة في درجة واحدة لتحديد حالات جديدة للتعليق.في هذه الورقة، نطبق طريقتين للحصول على درجات تجميع عبر المسندات المتعددة من أجل اختيار جمل الاستعلام مع طريقتين تقدير اليقين النموذجي: استخدام مخرجات الشبكة العصبية واستخدام التعلم النشط في Bayesian في التسرب عن طريق الخلاف.قارنا هذه الأساليب بثلاثة أسماطية سلبية --- اختيار الجملة العشوائية، تحديد المستندات العشوائية بالكامل، واختيار الجمل مع معظم المتوقع --- وتحليل تأثير هذه الاستراتيجيات لديها على منحنى التعلم فيما يتعلق بتخفيض عدد المشروحالجمل والمسند لتحقيق الأداء العالي.
Active learning has been shown to reduce annotation requirements for numerous natural language processing tasks, including semantic role labeling (SRL). SRL involves labeling argument spans for potentially multiple predicates in a sentence, which makes it challenging to aggregate the numerous decisions into a single score for determining new instances to annotate. In this paper, we apply two ways of aggregating scores across multiple predicates in order to choose query sentences with two methods of estimating model certainty: using the neural network's outputs and using dropout-based Bayesian Active Learning by Disagreement. We compare these methods with three passive baselines --- random sentence selection, random whole-document selection, and selecting sentences with the most predicates --- and analyse the effect these strategies have on the learning curve with respect to reducing the number of annotated sentences and predicates to achieve high performance.
References used
https://aclanthology.org/
In this work, we empirically compare span extraction methods for the task of semantic role labeling (SRL). While recent progress incorporating pre-trained contextualized representations into neural encoders has greatly improved SRL F1 performance on
Large-scale language models such as ELMo and BERT have pushed the horizon of what is possible in semantic role labeling (SRL), solving the out-of-vocabulary problem and enabling end-to-end systems, but they have also introduced significant biases. We
While FrameNet is widely regarded as a rich resource of semantics in natural language processing, a major criticism concerns its lack of coverage and the relative paucity of its labeled data compared to other commonly used lexical resources such as P
Although recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervis
High-quality arguments are an essential part of decision-making. Automatically predicting the quality of an argument is a complex task that recently got much attention in argument mining. However, the annotation effort for this task is exceptionally