Zhou, Guangyou*;Xie, Zhiwen;Huang, Jimmy Xiangji;He, Tingting
通讯作者：
Zhou, Guangyou
作者机构：
[Zhou, Guangyou; Xie, Zhiwen; He, Tingting] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
[Huang, Jimmy Xiangji] York Univ, Sch Informat Technol, Toronto, ON, Canada.
通讯机构：
[Zhou, Guangyou] C
Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
语种：
英文
期刊：
PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1
年：
2016
页码：
322-332
会议名称：
54th Annual Meeting of the Association-for-Computational-Linguistics (ACL)
会议时间：
AUG 07-12, 2016
会议地点：
Berlin, GERMANY
会议主办单位：
[Zhou, Guangyou;Xie, Zhiwen;He, Tingting] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.^[Huang, Jimmy Xiangji] York Univ, Sch Informat Technol, Toronto, ON, Canada.
会议赞助商：
Assoc Computat Linguist, Google, Baidu, Amazon Com, Bloomberg, Facebook, Microsoft Res, eBay, Elsevier, IBM Res, MaluubA, Huawei Technologies, Nuance, Grammarly, VoiceBox Technologies, Yandex, Textkernel, Zalando SE
主编：
Erk, K Smith, NA
出版地：
209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
出版者：
ASSOC COMPUTATIONAL LINGUISTICS-ACL
ISBN：
978-1-945626-00-5
基金类别：
National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61303180, 61573163]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [CCNU15ZD003, CCNU16A02024]; Natural Sciences and Engineering Research Council (NSERC) of CanadaNatural Sciences and Engineering Research Council of Canada (NSERC); NSERC CREATE award
机构署名：
本校为第一且通讯机构
院系归属：
计算机学院
摘要：
Sentiment classification aims to automatically predict sentiment polarity (e.g., positive or negative) of user generated sentiment data (e.g., reviews, blogs). Due to the mismatch among different domains, a sentiment classifier trained in one domain may not work well when directly applied to other domains. Thus, domain adaptation for sentiment classification algorithms are highly desirable to reduce the domain discrepancy and manual labeling costs. To address the above challenge, we propose a novel domain adaptation method, called Bi-Transferring Deep Neural Networks (BTDNNs). The proposed BTD...
