يقلل اعتراف الكيان المسمى بشكل مسمى (DS-NER) بكفاءة تكاليف العمالة بل في الوقت نفسه يعاني من ضوضاء الملصقات بسبب الافتراض القوي للإشراف البعيد.عادة ما تشتمل الحالات المسماة بشكل خاطئ على أرقام التعليقات التوضيحية غير المكتملة وغير الدقيقة، في حين أن معظم أعمال Denoising السابقة تشعر بالقلق فقط بنوع من الضوضاء وتفشل في استكشاف معلومات مفيدة بالكامل في مجموعة التدريب.لمعالجة هذه المشكلة، نقترح نماذج تعليمية قوية تسمى التعلم التعاوني الذاتي التعاونية (SCDL)، والتي تدرب بشاشات اثنين من شبكات الطلاب المعلمين بطريقة منفعة متبادلة لتنفيذ مصفاة التسمية الصاخبة بشكل متكرر.تم تصميم كل شبكة لاستغلال ملصقات موثوقة عبر Denoising الذاتي، ويتواصل شبكتان مع بعضهما البعض لاستكشاف التعليقات التوضيحية غير الموثوق بها من خلال تنظيم تعاوني.نتائج تجريبية واسعة النطاق على خمسة مجموعات بيانات حقيقية عالمية توضح أن SCDL متفوقة على طرق DS-NER DENOSION حول DS-NER.
Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotations, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods.
References used
https://aclanthology.org/
Distantly supervised models are very popular for relation extraction since we can obtain a large amount of training data using the distant supervision method without human annotation. In distant supervision, a sentence is considered as a source of a
We explore the application of state-of-the-art NER algorithms to ASR-generated call center transcripts. Previous work in this domain focused on the use of a BiLSTM-CRF model which relied on Flair embeddings; however, such a model is unwieldy in terms
While named entity recognition (NER) from speech has been around as long as NER from written text has, the accuracy of NER from speech has generally been much lower than that of NER from text. The rise in popularity of spoken dialog systems such as S
Scientific literature analysis needs fine-grained named entity recognition (NER) to provide a wide range of information for scientific discovery. For example, chemistry research needs to study dozens to hundreds of distinct, fine-grained entity types
Nowadays, named entity recognition (NER) achieved excellent results on the standard corpora. However, big issues are emerging with a need for an application in a specific domain, because it requires a suitable annotated corpus with adapted NE tag-set