Generating Summaries with Topic Templates and Structured Convolutional Decoders
By Laura Perez-Beltrachini, Yang Liu, Mirella Lapata. 2019
46 citations recorded by the source corpus.
Existing neural generation approaches create multi-sentence text as a single sequence. In this paper we propose a structured convolutional decoder that is guided by the content structure of target summaries. We compare our model with existing sequential decoders on three data sets representing different domains. Automatic and human evaluation demonstrate that our summaries have better content coverage.
Subfields: Artificial Intelligence, Molecular Biology
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
- Sebastian Gehrmann
- Percy Liang
- Mohit Bansal
- Elizabeth Clark
- Mirella Lapata
- Yejin Choi
- Caiming Xiong
- Graham Neubig
In Molecular Biology
- Mirella Lapata
- Laura Perez-Beltrachini
- Percy Liang
- Leonardo F. R. Ribeiro
- Elizabeth Clark
- Alex Wang
- Daniel Deutsch
- Michael. White
Citations in the corpus
- MLSUM: The Multilingual Summarization Corpus (2020, neutral): “A natural application of this data for summarization would be for template based summarization (Perez-Beltrachini et al., 2019), using it as additional features.”
- Models and Datasets for Cross-Lingual Summarisation (2022, methodology): “1 Inspired by past research on monolingual descriptive summarisation (Sauper and Barzilay, 2009; Zopf, 2018; Liu et al., 2018; Liu and Lapata, 2019a; Perez-Beltrachini et al., 2019; Hayashi et al., 2021), we derive cross-1 lingual datasets from Wikipedia 2 , which we collectively refer to as XWikis.”
- GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022, methodology): “, WikiCatSum (Perez-Beltrachini et al., 2019) and XLSum (Hasan et al.”