Knowledge Commons of Institute of Automation,CAS
Modeling Transferable Topics for Cross-Target Stance Detection | |
Penghui Wei1,2; Wenji Mao1,2 | |
2019-07 | |
会议名称 | The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval |
会议日期 | 2019-7 |
会议地点 | Paris, France |
出版者 | ACM |
摘要 | Targeted stance detection aims to classify the attitude of an opinionated text towards a pre-defined target. Previous methods mainly focus on in-target setting that models are trained and tested using data specific to the same target. In practical cases, the target we concern may have few or no labeled data, which restrains us from training a target-specific model. In this paper we study the problem of cross-target stance detection, utilizing labeled data of a source target to learn models that can be adapted to a destination target. To this end, we propose an effective method, the core intuition of which is to leverage shared latent topics between two targets as transferable knowledge to facilitate model adaptation. Our method acquires topic knowledge with neural variational inference, and further adopts adversarial training that encourages the model to learn target-invariant representations. Experimental results verify that our proposed method is superior to the state-of-the-art methods. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 自然语言处理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44759 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Wenji Mao |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Penghui Wei,Wenji Mao. Modeling Transferable Topics for Cross-Target Stance Detection[C]:ACM,2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
[2019SIGIR] Modeling(1556KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Penghui Wei]的文章 |
[Wenji Mao]的文章 |
百度学术 |
百度学术中相似的文章 |
[Penghui Wei]的文章 |
[Wenji Mao]的文章 |
必应学术 |
必应学术中相似的文章 |
[Penghui Wei]的文章 |
[Wenji Mao]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论