paper-with-me

홈 › Papers

A text autoencoder from transformer for fast encoding language representation

2021-11-04 · Tan Huang

In recent years BERT shows apparent advantages and great potential in natural language processing tasks. However, both training and applying BERT requires intensive time and resources for computing contextual language representations, which hinders its universality and applicability. To overcome this bottleneck, we propose a deep bidirectional language model by using window masking mechanism at attention layer. This work computes contextual language representations without random masking as does in BERT and maintains the deep bidirectional architecture like BERT. To compute the same sentence representation, our method shows O(n) complexity less compared to other transformer-based models with O($n^2$). To further demonstrate its superiority, computing context language representations on CPU environments is conducted, by using the embeddings from the proposed method, logistic regression shows much higher accuracy in terms of SMS classification. Moverover, the proposed method also achieves significant higher performance in semantic similarity tasks.

📄 PDF Abstract BibTeX arXiv:2111.02844

Code (0)

등록된 구현이 없습니다.

Tasks

CPULanguage ModelingLanguage ModellingSemantic SimilaritySemantic Textual SimilaritySentence

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 &…
WordPiece 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
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

Encoding Musical Style with Transformer Autoencoders

2019-12-10 · ICML 2020 1 · Kristy Choi, Curtis Hawthorne, Ian Simon, Monica Dinculescu 외

We consider the problem of learning high-level controls over the global structure of generated sequences, particularly in the context of symbolic music generation with complex language models. In this work, we present th…

Music Generation

Learning the Koopman Operator using Attention Free Transformers

2026-06-22 · Mohammed Nagdi, Evangelos-Marios Nikolados, Alexey Yermakov, Mars Gao 외 arxiv

Learning Koopman operators with autoencoders enables linear prediction in a latent space, but long-horizon rollouts often drift off the learned manifold, leading to phase and amplitude errors on systems with switching, c…

Recurrent autoencoder with sequence-aware encoding

2020-09-15 · Robert Susik

Recurrent Neural Networks (RNN) received a vast amount of attention last decade. Recently, the architectures of Recurrent AutoEncoders (RAE) found many applications in practice. RAE can extract the semantically valuable …

Fast and Accurate Transformer-based Translation with Character-Level Encoding and Subword-Level Decoding

2021-11-16 · ACL ARR November 2021 11 · Anonymous

The Transformer translation model is fast to train and achieves state-of-the-art results for various translation tasks. However, unknown input words at test time remain a challenge for the Transformer, especially when …

DecoderTranslation

Spatio-Temporal Encoding of Brain Dynamics with Surface Masked Autoencoders

2023-08-10 · Simon Dahan, Logan Z. J. Williams, Yourong Guo, Daniel Rueckert 외

The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the …

Transfer Learning