Unsupervised Text Summarization via Mixed Model Back-Translation
Back-translation based approaches have recently lead to significant progress in unsupervised sequence-to-sequence tasks such as machine translation or style transfer. In this work, we extend the paradigm to the problem of learning a sentence summarization system from unaligned data. We present several initial models which rely on the asymmetrical nature of the task to perform the first back-translation step, and demonstrate the value of combining the data created by these diverse initialization methods. Our system outperforms the current state-of-the-art for unsupervised sentence summarization from fully unaligned data by over 2 ROUGE, and matches the performance of recent semi-supervised approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSentenceSentence SummarizationStyle TransferText SummarizationTranslationUnsupervised Sentence SummarizationUnsupervised Text SummarizationSimilar Papers 제목 키워드 기반
Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
Back-translation is widely known for its effectiveness for neural machine translation when little to no parallel data is available. In this approach, a source-to-target model is coupled with a target-to-source model and …
Code GenerationCode SummarizationMachine TranslationTranslationSalience Estimation with Multi-Attention Learning for Abstractive Text Summarization
Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translatio…
Abstractive Text SummarizationDecoderMachine TranslationText Summarization+1Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
Back-translation is widely known for its effectiveness in neural machine translation when there is little to no parallel data. In this approach, a source-to-target model is coupled with a target-to-source model trained i…
Code GenerationCode SummarizationMachine TranslationTranslationKnowledge-guided Unsupervised Rhetorical Parsing for Text Summarization
Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. To make the summarization results more faithful, thi…
DecoderKnowledge Base ConstructionRepresentation LearningText Summarization+1Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we …
Abstractive Text SummarizationOpinion SummarizationSentence