paper-with-me

홈 › Papers

Adversarial Domain Adaptation Using Artificial Titles for Abstractive Title Generation

2019-07-01 · ACL 2019 7 · Francine Chen, Yan-Ying Chen

A common issue in training a deep learning, abstractive summarization model is lack of a large set of training summaries. This paper examines techniques for adapting from a labeled source domain to an unlabeled target domain in the context of an encoder-decoder model for text generation. In addition to adversarial domain adaptation (ADA), we introduce the use of artificial titles and sequential training to capture the grammatical style of the unlabeled target domain. Evaluation on adapting to/from news articles and Stack Exchange posts indicates that the use of these techniques can boost performance for both unsupervised adaptation as well as fine-tuning with limited target data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Abstractive Text SummarizationArticlesDecoderDomain AdaptationText Generation

Similar Papers 제목 키워드 기반

LipKey: A Large-Scale News Dataset for Absent Keyphrases Generation and Abstractive Summarization

2022-10-01 · COLING 2022 10 · Fajri Koto, Timothy Baldwin, Jey Han Lau

Summaries, keyphrases, and titles are different ways of concisely capturing the content of a document. While most previous work has released the datasets of keyphrases and summarization separately, in this work, we intro…

Abstractive Text SummarizationDocument Summarization

AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization

2021-03-21 · NAACL 2021 4 · Tiezheng Yu, Zihan Liu, Pascale Fung

State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available. In this paper, we present a study of dom…

Abstractive Text SummarizationDomain Adaptation

Discriminative Adversarial Search for Abstractive Summarization

2020-02-24 · ICML 2020 1 · Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski 외

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…

Abstractive Text SummarizationDomain Adaptation

LipKey: A Large-Scale News Dataset with Abstractive Keyphrases and Their Benefits for Summarization

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

Summaries, keyphrases, and titles are different ways of concisely capturing the content of a document. While most previous work has addressed them separately, in this work, we jointly use the three elements via multi-tas…

Document Summarization

A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization

2017-07-21 · WS 2017 9 · Xinyu Hua, Lu Wang

We study the problem of domain adaptation for neural abstractive summarization. We make initial efforts in investigating what information can be transferred to a new domain. Experimental results on news stories and opini…

Abstractive Text SummarizationArticlesDomain Adaptation