Search Results for author: Kaiqiang Song

Found 9 papers, 8 papers with code

A New Approach to Overgenerating and Scoring Abstractive Summaries

1 code implementation NAACL 2021 Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and select admissible ones according to users' needs.

CATE: Computation-aware Neural Architecture Encoding with Transformers

1 code implementation14 Feb 2021 Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang

Our experiments show that CATE is beneficial to the downstream search, especially in the large search space.

Neural Architecture Search Representation Learning +1

Automatic Summarization of Open-Domain Podcast Episodes

no code implementations9 Nov 2020 Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, Fei Liu

Instead, we investigate several less-studied aspects of neural abstractive summarization, including (i) the importance of selecting important segments from transcripts to serve as input to the summarizer; (ii) striking a balance between the amount and quality of training instances; (iii) the appropriate summary length and start/end points.

Abstractive Text Summarization

Controlling the Amount of Verbatim Copying in Abstractive Summarization

1 code implementation23 Nov 2019 Kaiqiang Song, Bingqing Wang, Zhe Feng, Liu Ren, Fei Liu

In this paper, we present a neural summarization model that, by learning from single human abstracts, can produce a broad spectrum of summaries ranging from purely extractive to highly generative ones.

Abstractive Text Summarization Language Modelling

Structure-Infused Copy Mechanisms for Abstractive Summarization

1 code implementation COLING 2018 Kaiqiang Song, Lin Zhao, Fei Liu

In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from the source sentence to summary sentence.

Abstractive Text Summarization

Cannot find the paper you are looking for? You can Submit a new open access paper.