XtremeDistil: Multi-stage Distillation for Massive Multilingual Models
원문 초록
Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use knowledge distillation to compress these huge models into shallow ones. In this work we study knowledge distillation with a focus on multi-lingual Named Entity Recognition (NER). In particular, we study several distillation strategies and propose a stage-wise optimization scheme leveraging teacher internal representations that is agnostic of teacher architecture and show that it outperforms strategies employed in prior works. Additionally, we investigate the role of several factors like the amount of unlabeled data, annotation resources, model architecture and inference latency to name a few. We show that our approach leads to massive compression of MBERT-like teacher models by upto 35x in terms of parameters and 51x in terms of latency for batch inference while retaining 95% of its F1-score for NER over 41 languages.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Transformer-Based Named Entity Recognition for Automated Server Provisioning
HEProto: A Hierarchical Enhancing ProtoNet based on Multi-Task Learning for Few-shot Named Entity Recognition
Legal Entity Extraction using a Pointer Generator Network
Analysis Of Contextual and Non-Contextual Word Embedding Models For Hindi NER With Web Application For Data Collection
Object-aware Multimodal Named Entity Recognition in Social Media Posts with Adversarial Learning
A Deep Neural Network Model for the Task of Named Entity Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.