paper-with-me

홈 › Papers

BERT's output layer recognizes all hidden layers? Some Intriguing Phenomena and a simple way to boost BERT

2020-01-25 · Wei-Tsung Kao, Tsung-Han Wu, Po-Han Chi, Chun-Cheng Hsieh, Hung-Yi Lee

Although Bidirectional Encoder Representations from Transformers (BERT) have achieved tremendous success in many natural language processing (NLP) tasks, it remains a black box. A variety of previous works have tried to lift the veil of BERT and understand each layer's functionality. In this paper, we found that surprisingly the output layer of BERT can reconstruct the input sentence by directly taking each layer of BERT as input, even though the output layer has never seen the input other than the final hidden layer. This fact remains true across a wide variety of BERT-based models, even when some layers are duplicated. Based on this observation, we propose a quite simple method to boost the performance of BERT. By duplicating some layers in the BERT-based models to make it deeper (no extra training required in this step), they obtain better performance in the downstream tasks after fine-tuning.

📄 PDF Abstract BibTeX arXiv:2001.09309

Code (0)

등록된 구현이 없습니다.

Tasks

AllSentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Jump to Conclusions: Short-Cutting Transformers With Linear Transformations

2023-03-16 · Alexander Yom Din, Taelin Karidi, Leshem Choshen, Mor Geva

Transformer-based language models create hidden representations of their inputs at every layer, but only use final-layer representations for prediction. This obscures the internal decision-making process of the model and…

Decision MakingLanguage ModelingLanguage Modelling

GRUBERT: A GRU-Based Method to Fuse BERT Hidden Layers for Twitter Sentiment Analysis

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Leo Horne, Matthias Matti, Pouya Pourjafar, Zuowen Wang

In this work, we introduce a GRU-based architecture called GRUBERT that learns to map the different BERT hidden layers to fused embeddings with the aim of achieving high accuracy on the Twitter sentiment analysis task. T…

Sentiment AnalysisTwitter Sentiment Analysis

Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation

2021-11-01 · EMNLP 2021 11 · Yimeng Wu, Mehdi Rezagholizadeh, Abbas Ghaddar, Md Akmal Haidar 외

Intermediate layer matching is shown as an effective approach for improving knowledge distillation (KD). However, this technique applies matching in the hidden spaces of two different networks (i.e. student and teacher),…

Knowledge Distillation

Patient Knowledge Distillation for BERT Model Compression

2019-08-25 · IJCNLP 2019 11 · Siqi Sun, Yu Cheng, Zhe Gan, Jingjing Liu

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application …

Knowledge DistillationmodelModel Compression

Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection

2023-10-08 · Nayoung Choi

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings,…

Binary ClassificationLanguage ModelingLanguage ModellingRepresentation Learning+1