استخراج العلاقات الإشراف على نطاق واسع يستخدم على نطاق واسع في بناء قواعد المعرفة بسبب كفاءته العالية.ومع ذلك، فإن الحالات التي تم الحصول عليها تلقائيا ذات جودة منخفضة مع العديد من الكلمات غير ذات الصلة.بالإضافة إلى ذلك، يؤدي الافتراض القوي للإشراف البعيد إلى وجود جمل صاخبة في أكياس الجملة.في هذه الورقة، نقترح شبكة مراجعة متعددة الطبقات رواية (MLRN) التي تخفف من آثار ضوضاء مستوى الكلمات من خلال التأكيد على علاقات الجملة الداخلية قبل استخراج المعلومات ذات الصلة داخل الجمل.بعد ذلك، نركز طريقة تعليمية متعددة الاستخدامات متعددة الاستخدامات ومقاومة للضوضاء مقاومة للضوضاء لتصفية الجمل الصاخبة وكذلك تعيين الأوزان المناسبة إلى تلك ذات الصلة.تجارب واسعة على مجموعة بيانات اثنين نيويورك تايمز (NYT) تثبت أن نهجنا يحقق تحسينات كبيرة على الأساس.
Distantly supervised relation extraction is widely used in the construction of knowledge bases due to its high efficiency. However, the automatically obtained instances are of low quality with numerous irrelevant words. In addition, the strong assumption of distant supervision leads to the existence of noisy sentences in the sentence bags. In this paper, we propose a novel Multi-Layer Revision Network (MLRN) which alleviates the effects of word-level noise by emphasizing inner-sentence correlations before extracting relevant information within sentences. Then, we devise a balanced and noise-resistant Confidence-based Multi-Instance Learning (CMIL) method to filter out noisy sentences as well as assign proper weights to relevant ones. Extensive experiments on two New York Times (NYT) datasets demonstrate that our approach achieves significant improvements over the baselines.
References used
https://aclanthology.org/
We propose a multi-task, probabilistic approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs. To achieve this, we bias the latent space of senten
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
In relation extraction, distant supervision is widely used to automatically label a large-scale training dataset by aligning a knowledge base with unstructured text. Most existing studies in this field have assumed there is a great deal of centralize
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the gradual drift p
Aspect-based sentiment analysis (ABSA) mainly involves three subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification, which are typically handled in a separate or joint manner. However, previous approaches