Huiyu Sun

Huiyu Sun

Auto-generated profile, based on publicly available information

Huiyu Sun

New York University

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2015
Verified
Book Chapter
Closed access
PDF file
Zhili ZhouZhili Zhou
Zhili Zhou
HSHuiyu Sun
Huiyu Sun
RHRohan Harit
Rohan Harit
XCXianyi Chen
Xianyi Chen
XSXingming Sun
Xingming Sun

1 January 2022 in Computer Systems Science and Engineering
Verified
Journal Article
Open access
PDF file
HSHuiyu Sun
Huiyu Sun
RGRalph Grishman
Ralph Grishman
Log-linear models and more recently neural network models used for supervised relation extraction requires substantial amounts of training data and time, limiting the portability to new relations and domains. To this end, we propose a training representation based on the dependency paths between entities in a dependency tree which we call lexicalized dependency paths (LDPs). We show that this representation is fast, efficient and transparent. We further propose representations utilizing entity types and its subtypes to refine our model and alleviate the data sparsity problem. We apply lexicalized dependency paths to supervised learning using the ACE corpus and show that it can achieve similar performance level to other state-of-the-art methods and even surpass them on several categories.

1 January 2022 in Intelligent Automation and Soft Computing
Verified
Journal Article
Open access
PDF file
HSHuiyu Sun
Huiyu Sun
RGRalph Grishman
Ralph Grishman
Active learning methods which present selected examples from the corpus for annotation provide more efficient learning of supervised relation extraction models, but they leave the developer in the unenviable role of a passive informant. To restore the developer’s proper role as a partner with the system, we must give the developer an ability to inspect the extraction model during development. We propose to make this possible through a representation based on lexicalized dependency paths (LDPs) coupled with an active learner for LDPs. We apply LDPs to both simulated and real active learning with ACE as evaluation and a year’s newswire for training and show that simulated active learning greatly reduces annotation cost while maintaining similar performance level of supervised learning, while real active learning yields comparable performance to the state-of-the-art using a small number of annotations.


1 January 2018 in Computers, Materials & Continua
Verified
Journal Article
Closed access
HSHuiyu Sun
Huiyu Sun
SMSuzanne McIntosh
Suzanne McIntosh

1 November 2016
Verified
Book Chapter
Closed access
PDF file
HSHuiyu Sun
Huiyu Sun
RGRalph Grishman
Ralph Grishman
YWYingchao Wang
Yingchao Wang