تلقى الكشف عن اللغة الهجومية (القديم) اهتماما متزايدا بسبب تأثيرها المجتمعي.يوضح العمل الحديث أن الأساليب القائمة على المحولات ثنائية الاتجاه تحصل على أداء مثير للإعجاب في القديم.ومع ذلك، فإن هذه الأساليب تعتمد عادة على مجموعات البيانات القديمة ذات المسمى على نطاق واسع لتدريب النماذج.لمعالجة مسألة ندرة البيانات / التسمية في القديم، في هذه الورقة، نقترح نهج بسيط في مجال تكيف مجال بسيط ولكنه فعال لتدريب المحولات ثنائية الاتجاه.تقدم نهجنا إجراءات التدريب على التكيف (DA) إلى ألبرت، بحيث يمكنها استغلال البيانات المساعدة الفعالة من مجالات المصدر لتحسين الأداء القديم في مجال مستهدف.تظهر النتائج التجريبية على مجموعات البيانات القياسية أن نهجنا، ألبرت (دا)، يحصل على الأداء الحديثة في معظم الحالات.على وجه الخصوص، فإن نهجنا يستفيد بشكل كبير من الدروس الممثلة بشكل كبير وغير مصنوع من الأداء، مع تحسن كبير على ألبرت.
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 well-labeled OLD datasets for model training. To address the issue of data/label scarcity in OLD, in this paper, we propose a simple yet effective domain adaptation approach to train bidirectional transformers. Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain. Experimental results on benchmark datasets show that our approach, ALBERT (DA), obtains the state-of-the-art performance in most cases. Particularly, our approach significantly benefits underrepresented and under-performing classes, with a significant improvement over ALBERT.
References used
https://aclanthology.org/
Sarcasm detection is one of the top challenging tasks in text classification, particularly for informal Arabic with high syntactic and semantic ambiguity. We propose two systems that harness knowledge from multiple tasks to improve the performance of
Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To a
We propose a structured extension to bidirectional-context conditional language generation, or infilling,'' inspired by Frame Semantic theory. Guidance is provided through one of two approaches: (1) model fine-tuning, conditioning directly on observe
The goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target. Despite substantial progress on this task, one of the remaining challenges is the scarcity of annotations. Data augmentatio
The interest in offensive content identification in social media has grown substantially in recent years. Previous work has dealt mostly with post level annotations. However, identifying offensive spans is useful in many ways. To help coping with thi