Tag Recommendation by Word-Level Tag Sequence Modeling
X. Shi, H. Huang, S. Zhao, P. Jian, and Y. Tang. Database Systems for Advanced Applications, page 420--424. Cham, Springer International Publishing, (2019)
Abstract
In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder with local positional encodings for learning relations globally. Experimental results on Zhihu datasets illustrate the proposed model outperforms other state-of-the-art text classification based methods.
Description
Tag Recommendation by Word-Level Tag Sequence Modeling | SpringerLink
%0 Conference Paper
%1 shi2019recommendation
%A Shi, Xuewen
%A Huang, Heyan
%A Zhao, Shuyang
%A Jian, Ping
%A Tang, Yi-Kun
%B Database Systems for Advanced Applications
%C Cham
%D 2019
%E Li, Guoliang
%E Yang, Jun
%E Gama, Joao
%E Natwichai, Juggapong
%E Tong, Yongxin
%I Springer International Publishing
%K paper:neural_tag recommendation seq2seq tag
%P 420--424
%T Tag Recommendation by Word-Level Tag Sequence Modeling
%X In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder with local positional encodings for learning relations globally. Experimental results on Zhihu datasets illustrate the proposed model outperforms other state-of-the-art text classification based methods.
%@ 978-3-030-18590-9
@inproceedings{shi2019recommendation,
abstract = {In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder with local positional encodings for learning relations globally. Experimental results on Zhihu datasets illustrate the proposed model outperforms other state-of-the-art text classification based methods.},
added-at = {2019-07-01T22:53:18.000+0200},
address = {Cham},
author = {Shi, Xuewen and Huang, Heyan and Zhao, Shuyang and Jian, Ping and Tang, Yi-Kun},
biburl = {https://www.bibsonomy.org/bibtex/2e812f675b8cb81623b3a483c3111cf6d/nosebrain},
booktitle = {Database Systems for Advanced Applications},
description = {Tag Recommendation by Word-Level Tag Sequence Modeling | SpringerLink},
editor = {Li, Guoliang and Yang, Jun and Gama, Joao and Natwichai, Juggapong and Tong, Yongxin},
interhash = {02e437b6b540f944c96d48c2fcb6af29},
intrahash = {e812f675b8cb81623b3a483c3111cf6d},
isbn = {978-3-030-18590-9},
keywords = {paper:neural_tag recommendation seq2seq tag},
pages = {420--424},
publisher = {Springer International Publishing},
timestamp = {2019-07-01T22:53:18.000+0200},
title = {Tag Recommendation by Word-Level Tag Sequence Modeling},
year = 2019
}