يمكن أن تفحص نماذج استخراج أحداث المخدرات السلبية (ADE) بسرعة مجموعات كبيرة من نصوص وسائل التواصل الاجتماعي، والكشف عن ذكرات التفاعلات السلبية ذات الصلة بالمخدرات وتحريك التحقيقات الطبية.ومع ذلك، على الرغم من التقدم الأخير في NLP، فإنه غير معروف حاليا إذا كانت هذه النماذج قوية في مواجهة النفي، والتي تنتشر عبر أصناف اللغة.في هذه الورقة، نقيم ثلاث أنظمة ثلاثية، تظهر هشاشةها ضد النفي، ثم نقدم استراتيجيتين ممكنين لزيادة متانة هذه النماذج: نهج خط أنابيب، بالاعتماد على مكون محدد للكشف عن النفي؛تكبير بيانات استخراج ADE لإنشاء عينات نفي بشكل مصطنع وتدريب النماذج الأخرى.نظهر أن كلا الاستراتيجيتين تجلب الزيادات الكبيرة في الأداء، مما أدى إلى خفض عدد الكيانات الزائفة المتوقعة من النماذج.سيتم إصدار بيانات DataSet و Code علنا لتشجيع البحث على الموضوع.
Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations. However, despite the recent advances in NLP, it is currently unknown if such models are robust in face of negation, which is pervasive across language varieties. In this paper we evaluate three state-of-the-art systems, showing their fragility against negation, and then we introduce two possible strategies to increase the robustness of these models: a pipeline approach, relying on a specific component for negation detection; an augmentation of an ADE extraction dataset to artificially create negated samples and further train the models. We show that both strategies bring significant increases in performance, lowering the number of spurious entities predicted by the models. Our dataset and code will be publicly released to encourage research on the topic.
References used
https://aclanthology.org/
We present an algorithm based on multi-layer transformers for identifying Adverse Drug Reactions (ADR) in social media data. Our model relies on the properties of the problem and the characteristics of contextual word embeddings to extract two views
The paper researches the problem of drug adverse effect detection in texts of social media. We describe the development of such classification system for Russian tweets. To increase the train dataset we apply a couple of augmentation techniques and analyze their effect in comparison with similar systems presented at 2021 years' SMM4H Workshop.
This paper describes models developed for the Social Media Mining for Health (SMM4H) 2021 shared tasks. Our team participated in the first subtask that classifies tweets with Adverse Drug Effect (ADE) mentions. Our best performing model utilizes BERT
Challenging problems such as open-domain question answering, fact checking, slot filling and entity linking require access to large, external knowledge sources. While some models do well on individual tasks, developing general models is difficult as
Robust sequence-to-sequence modelling is an essential task in the real world where the inputs are often noisy. Both user-generated and machine generated inputs contain various kinds of noises in the form of spelling mistakes, grammatical errors, char