paper-with-me

홈 › Papers

Extremely Small BERT Models from Mixed-Vocabulary Training

2019-09-25 · EACL 2021 2 · Sanqiang Zhao, Raghav Gupta, Yang song, Denny Zhou

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input vocabulary and embedding dimensions. Existing knowledge distillation methods used for model compression cannot be directly applied to train student models with reduced vocabulary sizes. To this end, we propose a distillation method to align the teacher and student embeddings via mixed-vocabulary training. Our method compresses BERT-LARGE to a task-agnostic model with smaller vocabulary and hidden dimensions, which is an order of magnitude smaller than other distilled BERT models and offers a better size-accuracy trade-off on language understanding benchmarks as well as a practical dialogue task.

📄 PDF Abstract BibTeX arXiv:1909.11687

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationLanguage ModellingModel CompressionWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
BiLSTM A Bidirectional LSTM, or biLSTM, is a sequence processing model that consists of two LSTMs: one taking the input in a forward direction, and the other in a backwards…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…

Similar Papers 제목 키워드 기반

Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech

2022-03-31 · Guangyan Zhang, Kaitao Song, Xu Tan, Daxin Tan 외

Recently, leveraging BERT pre-training to improve the phoneme encoder in text to speech (TTS) has drawn increasing attention. However, the works apply pre-training with character-based units to enhance the TTS phoneme en…

text-to-speechText to Speech

BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining

2020-05-26 · EMNLP (ClinicalNLP) 2020 11 · Zachariah Zhang, Jingshu Liu, Narges Razavian

Clinical interactions are initially recorded and documented in free text medical notes. ICD coding is the task of classifying and coding all diagnoses, symptoms and procedures associated with a patient's visit. The proce…

exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Wen Tai, H. T. Kung, Xin Dong, Marcus Comiter 외

We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i.e., c…

Articles

Automatic Mixed-Precision Quantization Search of BERT

2021-12-30 · Changsheng Zhao, Ting Hua, Yilin Shen, Qian Lou 외

Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. However, these models usually contain millions of parameters, which prevents them from practical …

Knowledge DistillationModel CompressionNeural Architecture SearchQuantization

LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension

2022-12-16 · Wenyue Hua, Yuchen Zhang, Zhe Chen, Josie Li 외

The application of Natural Language Processing (NLP) to specialized domains, such as the law, has recently received a surge of interest. As many legal services rely on processing and analyzing large collections of docume…

Language ModelingLanguage ModellingReading Comprehension