paper-with-me

Papers

Simplified TinyBERT: Knowledge Distillation for Document Retrieval

2020-09-16 · Xuanang Chen, Ben He, Kai Hui, Le Sun, Yingfei Sun

Despite the effectiveness of utilizing the BERT model for document ranking, the high computational cost of such approaches limits their uses. To this end, this paper first empirically investigates the effectiveness of two knowledge distillation models on the document ranking task. In addition, on top of the recently proposed TinyBERT model, two simplifications are proposed. Evaluations on two different and widely-used benchmarks demonstrate that Simplified TinyBERT with the proposed simplifications not only boosts TinyBERT, but also significantly outperforms BERT-Base when providing 15$\times$ speedup.

📄 PDF Abstract BibTeX arXiv:2009.07531

Code (4)

2023-MindSpore-1/ms-code-220/tree/main/tinybert mindspore
Mind23-2/MindCode-149 mindspore
MindSpore-paper-code-3/code9/tree/main/tinybert mindspore
cxa-unique/Simplified-TinyBERT pytorch

Tasks

Document RankingKnowledge DistillationRetrieval

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.…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

TinyBERT: Distilling BERT for Natural Language Understanding

2019-09-23 · Findings of the Association for Computational Linguistics 2020 · Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang 외

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is diffi…

Knowledge DistillationLanguage ModellingLinguistic AcceptabilityNatural Language Inference+5

Knowledge Distillation of LLM for Automatic Scoring of Science Education Assessments

2023-12-26 · Ehsan Latif, Luyang Fang, Ping Ma, Xiaoming Zhai

This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these …

Knowledge DistillationMathematical Reasoning

Fine-Grained Distillation for Long Document Retrieval

2022-12-20 · Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao 외

Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encode…

Knowledge DistillationRetrieval

QuaLA-MiniLM: a Quantized Length Adaptive MiniLM

2022-10-31 · Shira Guskin, Moshe Wasserblat, Chang Wang, Haihao Shen

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. A knowledge distillation approach addresses the computational efficiency by self-distil…

Computational EfficiencyKnowledge DistillationQuantizationQuestion Answering

PROD: Progressive Distillation for Dense Retrieval

2022-09-27 · Zhenghao Lin, Yeyun Gong, Xiao Liu, Hang Zhang 외

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does n…

Knowledge DistillationNatural QuestionsRetrieval