paper-with-me

Papers

Unsupervised Pretraining for Sequence to Sequence Learning

2017-09-01 · EMNLP 2017 9 · Ramach, Prajit ran, Peter Liu, Quoc Le

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights of two language models and then fine-tuned with labeled data. We apply this method to challenging benchmarks in machine translation and abstractive summarization and find that it significantly improves the subsequent supervised models. Our main result is that pretraining improves the generalization of seq2seq models. We achieve state-of-the-art results on the WMT English→German task, surpassing a range of methods using both phrase-based machine translation and neural machine translation. Our method achieves a significant improvement of 1.3 BLEU from th previous best models on both WMT{'}14 and WMT{'}15 English→German. We also conduct human evaluations on abstractive summarization and find that our method outperforms a purely supervised learning baseline in a statistically significant manner.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationDecoderLanguage ModelingLanguage ModellingMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

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…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

2019-04-04 · IJCNLP 2019 11 · Xiaochuang Han, Jacob Eisenstein

Contextualized word embeddings such as ELMo and BERT provide a foundation for strong performance across a wide range of natural language processing tasks by pretraining on large corpora of unlabeled text. However, the ap…

Domain AdaptationLanguage ModelingLanguage ModellingMasked Language Modeling+3

Unsupervised Pretraining for Sequence to Sequence Learning

2016-11-08 · EMNLP 2017 9 · Prajit Ramachandran, Peter J. Liu, Quoc V. Le

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with th…

Abstractive Text SummarizationDecoderMachine TranslationTranslation

Semi-supervised Sequence Learning

2015-11-04 · NeurIPS 2015 12 · Andrew M. Dai, Quoc V. Le

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural la…

Language ModelingLanguage ModellingText Classification

Continuous Sign Language Recognition with Adapted Conformer via Unsupervised Pretraining

2024-05-20 · Neena Aloysius, Geetha M, Prema Nedungadi

Conventional Deep Learning frameworks for continuous sign language recognition (CSLR) are comprised of a single or multi-modal feature extractor, a sequence-learning module, and a decoder for outputting the glosses. The …

Sign Language Recognitionspeech-recognitionSpeech Recognition

Exploring Unsupervised Pretraining Objectives for Machine Translation

2021-06-10 · Findings (ACL) 2021 8 · Christos Baziotis, Ivan Titov, Alexandra Birch, Barry Haddow

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to se…

DecoderLanguage ModelingLanguage ModellingMachine Translation+3