الاستعارات في كل مكان في اللغة الطبيعية، ويتطلب الكشف عنها منطق سياقي حول ما إذا كان التعارض الدلالي موجود بالفعل.معظم العمل الحالي يعالج هذه المشكلة باستخدام نماذج السياق المدربة مسبقا.على الرغم من نجاحها، تتطلب هذه النماذج كمية كبيرة من البيانات المسمى ولا تستند إلى اللغة اللاحنة.في هذه الورقة، اقترحنا نموذجا متمربا مسبقا مسبقا (كيت) للكشف عن الاستعارة مع التعلم شبه الإشرافه.يستخدم نموذجنا أولا نموذجا مدربا مسبقا للحصول على تمثيل سياقي للكلمات المستهدفة وتوظف هدفا بسيطا لتعزيز المسافة المتزايدة بين الكلمات المستهدفة "الحواس الحرفية والجهزة المجازية القائمة على نظريات لغوية.علاوة على ذلك، نقترح استراتيجية بسيطة لجمع مثيلات مرشحة واسعة النطاق من كوربوس العام وتعميم النموذج عبر التدريب الذاتي.تبين تجارب واسعة أن كيت يحقق أداء أفضل ضد خطوط خطوط البيانات الحديثة على العديد من البيانات القياسية.
Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists. Most existing work addresses this problem using pre-trained contextualized models. Despite their success, these models require a large amount of labeled data and are not linguistically-based. In this paper, we proposed a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning. Our model first uses a pre-trained model to obtain a contextual representation of target words and employs a contrastive objective to promote an increased distance between target words' literal and metaphorical senses based on linguistic theories. Furthermore, we propose a simple strategy to collect large-scale candidate instances from the general corpus and generalize the model via self-training. Extensive experiments show that CATE achieves better performance against state-of-the-art baselines on several benchmark datasets.
References used
https://aclanthology.org/
In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints:
Meta learning aims to optimize the model's capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world few shot learning scenarios. Rec
Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning pre-trained LMs u
Toxic comments contain forms of non-acceptable language targeted towards groups or individuals. These types of comments become a serious concern for government organizations, online communities, and social media platforms. Although there are some app
Hope is an essential aspect of mental health stability and recovery in every individual in this fast-changing world. Any tools and methods developed for detection, analysis, and generation of hope speech will be beneficial. In this paper, we propose