Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media

doi:10.1145/3644074

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统认知与决策实验室

	Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media
	Liu, Jie 3,4; Li, Yaguang 6; He, Shizhu 1; Wu, Shun 1; Liu, Kang 1; Liu, Shenping 2; Wang, Jiong 6; Zhang, Qing 4,5
刊名	ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
	2024-03-01
卷号	23 期号:3 页码:20
关键词	Social media reply keyword prediction text generation multi-label classification determinantal point processes
ISSN号	2375-4699
DOI	10.1145/3644074
通讯作者	Zhang, Qing(zqicl@ncut.edu.cn)
英文摘要	Social media produces large amounts of content every day. How to predict the potential influences of the contents from a social reply feedback perspective is a key issue that has not been explored. Thus, we propose a novel task named reply keyword prediction in social media, which aims to predict the keywords in the potential replies in as many aspects as possible. One prerequisite challenge is that the accessible social media datasets labeling such keywords remain absent. To solve this issue, we propose a new dataset,1 to study the reply keyword prediction in social media. This task could be seen as a single-turn dialogue keyword prediction for open-domain dialogue system. However, existing methods for dialogue keyword prediction cannot be adopted directly, which has two main drawbacks. First, they do not provide an explicit mechanism to model topic complementarity between keywords which is crucial in social media to controllably model all aspects of replies. Second, the collocations of keywords are not explicitly modeled, which also makes it less controllable to optimize for fine-grained prediction since the context information is much less than that in dialogue. To address these issues, we propose a two-stage disentangled framework, which can optimize the complementarity and collocation explicitly in a disentangled fashion. In the first stage, we use a sequence-to-set paradigm via multi-label prediction and determinantal point processes, to generate a set of keyword seeds satisfying the complementarity. In the second stage, we adopt a set-to-sequence paradigm via seq2seq model with the keyword seeds guidance from the set, to generate the more-fine-grained keywords with collocation. Experiments show that this method can generate not only a more diverse set of keywords but also more relevant and consistent keywords. Furthermore, the keywords obtained based on this method can achieve better reply generation results in the retrieval-based system than others.
资助项目	National Key Research and Development Program of China[2020AAA0109703] ; National Natural Science Foundation of China[62076167] ; Beijing Municipal Education Commission-Beijing Natural Fund Joint Funding Project[KZ201910028039]
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:001208772400007
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Municipal Education Commission-Beijing Natural Fund Joint Funding Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/56993]
专题	复杂系统认知与决策实验室
通讯作者	Zhang, Qing
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Beijing Unisound Informat Technol Co Ltd, Beijing, Peoples R China 3.Capital Normal Univ, China Language Intelligence Res Ctr, Beijing, Peoples R China 4.North China Univ Technol, Sch Informat Sci, Beijing, Peoples R China 5.CNONIX Natl Standard Applicat & Promot Lab, Beijing, Peoples R China 6.Capital Normal Univ, Coll Informat Engn, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Jie,Li, Yaguang,He, Shizhu,et al. Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media[J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,2024,23(3):20.
APA	Liu, Jie.,Li, Yaguang.,He, Shizhu.,Wu, Shun.,Liu, Kang.,...&Zhang, Qing.(2024).Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media.ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING,23(3),20.
MLA	Liu, Jie,et al."Seq2Set2Seq: A Two-stage Disentangled Method for Reply Keyword Generation in Social Media".ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 23.3(2024):20.