activity
20182021
most citedControlling the Amount of Verbatim Copying in Abstractive Summarization

4 citations · 5 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CL2021

Modeling Endorsement for Multi-Document Abstractive Summarization

Logan Lebanoff, Bingqing Wang, Zhe Feng +1

A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of…

cs.CL2021

GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition

Xinyan Zhao, Haibo Ding, Zhe Feng

Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling…

cs.CL20211 cited

A New Approach to Overgenerating and Scoring Abstractive Summaries

Kaiqiang Song, Bingqing Wang, Zhe Feng +1

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' ne…

cs.LG2021

CATE: Computation-aware Neural Architecture Encoding with Transformers

Shen Yan, Kaiqiang Song, Fei Liu +1

Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structu…

cs.CL20194 cited

Controlling the Amount of Verbatim Copying in Abstractive Summarization

Kaiqiang Song, Bingqing Wang, Zhe Feng +2

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 copying while still allowing for text abstrac…

cs.CV2018

Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection

Ahmed Imtiaz Humayun, Shabnam Ghaffarzadegan, Zhe Feng +1

Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The state-of-the-art algorithms f…