A Robust Abstractive System for Cross-Lingual Summarization
By Jessica Ouyang, Boya Song, K. McKeown. 2019
61 citations recorded by the source corpus.
We present a robust neural abstractive summarization system for cross-lingual summarization. We construct summarization corpora for documents automatically translated from three low-resource languages, Somali, Swahili, and Tagalog, using machine translation and the New York Times summarization corpus. We train three language-specific abstractive summarizers and evaluate on documents originally written in the source languages, as well as on a fourth, unseen language: Arabic. Our systems achieve significantly higher fluency than a standard copy-attention summarizer on automatically translated input documents, as well as comparable content selection.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mirella Lapata
- Mohit Bansal
- Claire Cardie
- Laura Perez-Beltrachini
- Thomas Scialom
- Yejin Choi
- Hal Daumé Iii
- Jacopo Staiano
In Natural Language Processing
- Hal Daumé Iii
- Laura Perez-Beltrachini
- Thomas Scialom
- Claire Cardie
- Mirella Lapata
- Faisal Ladhak
- Mohit Bansal
- K. McKeown
Citations in the corpus
- WikiLingua: A New Benchmark Dataset for Multilingual Abstractive Summarization (2020, methodology): “Following the prior work in cross-lingual abstrac-tive summarization (Nguyen and Daum´e III, 2019; Ouyang et al., 2019), we aim to generate English summaries from non-English articles, as an initial study.”
- MLSUM: The Multilingual Summarization Corpus (2020, methodology): “Ouyang et al. (2019) proposed to learn summarization models for three low-resource languages (Somali, Swahili, and Tagalog), by using an automated translation of the New York Times dataset..”
- Models and Datasets for Cross-Lingual Summarisation (2022, background): “, 2020), translate the input documents (Ouyang et al., 2019), or build document-summary pairs from social media annotations and crowd-sourcing (Nguyen and Daumé III, 2019).”
- NCLS: Neural Cross-Lingual Summarization (2019, methodology): “Ouyang et al. (2019) present a robust abstractive summarization system for low resource languages where no summarization corpora are currently available.”
- Global Voices: Crossing Borders in Automatic News Summarization (2019, background): “Previous work on cross-lingual summarization performs evaluation with human judgments (Orsan and Chiorean, 2008), or with automatic metrics and noisy source articles generated by automatic translation systems (Wan et al., 2010; Ouyang et al., 2019).”