يعد تدريب الاتساق غير الخاضع للتناسق طريقة للتعلم شبه الإشرافه يشجع الاتساق في التنبؤات النموذجية بين البيانات الأصلية والمعزز.للحصول على التعرف على الكيان المسمى (NER)، زيادة النهج الحالية تسلسل الإدخال مع استبدال الرمز المميز، بافتراض التعليقات التوضيحية على المناصب المستبدة دون تغيير.في هذه الورقة، نستكشف استخدام إعادة الصياغة كمخطط تعزز البيانات أكثر مبدئيا للتدريب على الاتساق غير المدعوم.على وجه التحديد، نقوم بتحويل المجال العشوائي الشرطي (CRF) إلى وحدة تصنيف متعدد العلامات وتشجيع الاتساق على مظهر الكيان بين التسلسلات الأصلية المعززة.تبين التجارب أن طريقتنا فعالة بشكل خاص عندما تكون التعليقات التوضيحية محدودة.
Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data. For Named Entity Recognition (NER), existing approaches augment the input sequence with token replacement, assuming annotations on the replaced positions unchanged. In this paper, we explore the use of paraphrasing as a more principled data augmentation scheme for NER unsupervised consistency training. Specifically, we convert Conditional Random Field (CRF) into a multi-label classification module and encourage consistency on the entity appearance between the original and paraphrased sequences. Experiments show that our method is especially effective when annotations are limited.
References used
https://aclanthology.org/
Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and inves
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled d
Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not the case in numerous domains. We propose a light-weight and scalable
In this paper, we present the systems submitted by our team from the Institute of ICT (HEIG-VD / HES-SO) to the Unsupervised MT and Very Low Resource Supervised MT task. We first study the improvements brought to a baseline system by techniques such
Cross-domain Named Entity Recognition (NER) transfers the NER knowledge from high-resource domains to the low-resource target domain. Due to limited labeled resources and domain shift, cross-domain NER is a challenging task. To address these challeng