paper-with-me

홈 › Papers

Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning

2020-04-17 · ACL 2020 6 · Joongbo Shin, Yoonhyung Lee, Seunghyun Yoon, Kyomin Jung

Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language representations. To resolve the limitation, we propose a novel deep bidirectional language model called Transformer-based Text Autoencoder (T-TA). The T-TA computes contextual language representations without repetition and has benefits of the deep bidirectional architecture like BERT. In run-time experiments on CPU environments, the proposed T-TA performs over six times faster than the BERT-based model in the reranking task and twelve times faster in the semantic similarity task. Furthermore, the T-TA shows competitive or even better accuracies than those of BERT on the above tasks.

📄 PDF Abstract BibTeX arXiv:2004.08097

Code (1)

joongbo/tta 공식 구현 tf

Tasks

CPULanguage ModelingLanguage ModellingRerankingSemantic SimilaritySemantic Textual Similarity

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Solana Customer Service Number +1-833-534-1729 설명 없음
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…

Similar Papers 제목 키워드 기반

Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation

2019-07-01 · ACL 2019 7 · Du{\v{s}}an Vari{\v{s}}, Ond{\v{r}}ej Bojar

This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with …

DecoderLanguage ModelingLanguage ModellingMachine Translation+2

Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation

2020-10-19 · Dušan Variš, Ondřej Bojar

This work presents our ongoing research of unsupervised pretraining in neural machine translation (NMT). In our method, we initialize the weights of the encoder and decoder with two language models that are trained with …

DecoderLanguage ModelingLanguage ModellingMachine Translation+2

Contextual Salience for Fast and Accurate Sentence Vectors

2018-03-22 · Eric Zelikman, Richard Socher

Unsupervised vector representations of sentences or documents are a major building block for many language tasks such as sentiment classification. However, current methods are uninterpretable and slow or require large tr…

Document SummarizationGeneral ClassificationSentenceSentence Embeddings+2

Transformer Based Language Models for Similar Text Retrieval and Ranking

2020-05-10 · Javed Qadrud-Din, Ashraf Bah Rabiou, Ryan Walker, Ravi Soni 외

Most approaches for similar text retrieval and ranking with long natural language queries rely at some level on queries and responses having words in common with each other. Recent applications of transformer-based neura…

Natural Language QueriesRetrievalSentenceText Retrieval

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 re…

CPULanguage ModelingLanguage ModellingSemantic Similarity+2