summarization

Unsupervised Multi-document Summarization with Holistic Inference
Multi-document summarization aims to obtain core information from a collection of documents written on the same topic. This paper …
Haopeng Zhang, Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Jiawei Zhang, Dong Yu
PDF Cite
Generating User-Engaging News Headlines
The potential choices for news article headlines are enormous, and finding the right balance between conveying the essential message …
Pengshan Cai, Kaiqiang Song, Sangwoo Cho, Hongwei Wang, Xiaoyang Wang, Hong Yu, Dong Yu
PDF Cite DOI
OASum: Large-Scale Open Domain Aspect-based Summarization
Aspect or query-based summarization has recently caught more attention, as it can generate differentiated summaries based on users’ …
Xianjun Yang, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Xiaoman Pan, Linda Petzold, Dong Yu
PDF Cite Code Dataset DOI
NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization
Narrative summarization aims to produce a distilled version of a narrative to describe its most salient events and characters. Writing …
Chao Zhao, Faeze Brahman, Kaiqiang Song, Wenlin Yao, Dian Yu, Snigdha Chaturvedi
PDF Cite Code DOI
Salience Allocation as Guidance for Abstractive Summarization
Abstractive summarization models typically learn to capture the salient information from scratch implicitly. Recent literature adds …
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu
PDF Cite Code DOI
Toward Unifying Text Segmentation and Long Document Summarization
Text segmentation is important for signaling a document’s structure. Without segmenting a long document into topically coherent …
Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu, Dong Yu
PDF Cite Code DOI
Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension
Comprehending a dialogue requires a model to capture diverse kinds of key information in the utterances, which are either scattered …
Chao Zhao, Wenlin Yao, Dian Yu, Kaiqiang Song, Dong Yu, Jianshu Chen
PDF Cite Code DOI
Towards Abstractive Grounded Summarization of Podcast Transcripts
Podcasts have shown a recent rise in popularity. Summarization of podcasts is of practical benefit to both content providers and …
Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, Fei Liu
PDF Cite Code DOI
A New Approach to Overgenerating and Scoring Abstractive Summaries
We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and …
Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu
PDF Cite Code Video DOI
Automatic Summarization of Open-Domain Podcast Episodes
We present implementation details of our abstractive summarizers that achieve competitive results on the Podcast Summarization task of …
Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, Fei Liu
PDF Cite DOI