Discriminative Adversarial Search for Abstractive Summarization
We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics. Inspired by Generative Adversarial Networks (GANs), wherein a discriminator is used to improve the generator, our method differs from GANs in that the generator parameters are not updated at training time and the discriminator is only used to drive sequence generation at inference time. We investigate the effectiveness of the proposed approach on the task of Abstractive Summarization: the results obtained show that a naive application of DAS improves over the state-of-the-art methods, with further gains obtained via discriminator retraining. Moreover, we show how DAS can be effective for cross-domain adaptation. Finally, all results reported are obtained without additional rule-based filtering strategies, commonly used by the best performing systems available: this indicates that DAS can effectively be deployed without relying on post-hoc modifications of the generated outputs.
Code (1)
Tasks
Abstractive Text SummarizationDomain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generative Adversarial Network for Abstractive Text Summarization
In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent…
Abstractive Text SummarizationGenerative Adversarial Networkreinforcement-learningReinforcement Learning+2Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vuln…
Abstractive Text SummarizationRobust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vuln…
Abstractive Text SummarizationAbstractive Text Summarization by Incorporating Reader Comments
In neural abstractive summarization field, conventional sequence-to-sequence based models often suffer from summarizing the wrong aspect of the document with respect to the main aspect. To tackle this problem, we propose…
Abstractive Text SummarizationReader-Aware SummarizationText SummarizationDeep Recurrent Generative Decoder for Abstractive Text Summarization
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN). Latent structure information implie…
Abstractive Text SummarizationDecoderText SummarizationVariational Inference