KaiqiangSong
KaiqiangSong
Home
Experience
Publications
Contact
Light
Dark
Automatic
nlp
Open-Domain Event Graph Induction for Mitigating Framing Bias
Researchers have proposed various information extraction (IE) techniques to convert news articles into structured knowledge for news …
Siyi Liu
,
Hongming Zhang
,
Hongwei Wang
,
Kaiqiang Song
,
Dan Roth
,
Dong Yu
PDF
Cite
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
Better Highlighting: Creating Sub-Sentence Summary Highlights
Amongst the best means to summarize is highlighting. In this paper, we aim to generate summary highlights to be overlaid on the …
Sangwoo Cho
,
Kaiqiang Song
,
Chen Li
,
Dong Yu
,
Hassan Foroosh
,
Fei Liu
PDF
Cite
Code
Video
DOI
Controlling the Amount of Verbatim Copying in Abstractive Summarization
An abstract must not change the meaning of the original text. A single most effective way to achieve that is to increase the amount of …
Kaiqiang Song
,
Bingqing Wang
,
Zhe Feng
,
Ren Liu
,
Fei Liu
PDF
Cite
Code
DOI
«
»
Cite
×