Task-oriented keyphrase extraction from social media
文献类型：期刊论文
| 作者 | Wei Zhao; Jia Zhu; Qiang Qu; Wei Xu; YuZhi Liang; Min Yang |
| 刊名 | Multimedia Tools and Applications
 |
| 出版日期 | 2017 |
| 文献子类 | 期刊论文 |
| 英文摘要 | Keyphrase extraction from social media is a crucial and challenging task. Previous studies usually focus on extracting keyphrases that provide the summary of a corpus. However, they do not take users’ specific needs into consideration. In this paper, we propose a novel three-stage model to learn a keyphrase set that represents or related to a particular topic. Firstly, a phrase mining algorithm is applied to segment the documents into human-interpretable phrases. Secondly, we propose a weakly supervised model to extract candidate keyphrases, which uses a few pre-specific seed keyphrases to guide the model. The model consequently makes the extracted keyphrases more specific and related to the seed keyphrases (which reflect the user’s needs). Finally, to further identify the implicitly related phrases, the PMI-IR algorithm is employed to obtain the synonyms of the extracted candidate keyphrases. We conducted experiments on two publicly available datasets from news and Twitter. The experimental results demonstrate that our approach outperforms the state-of-the-art baselines and has the potential to extract high-quality task-oriented keyphrases. |
| URL标识 | 查看原文 |
| 语种 | 英语 |
| WOS记录号 | WOS:000425132600014 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/11925]  |
| 专题 | 深圳先进技术研究院_其他 |
| 作者单位 | Multimedia Tools and Applications |
| 推荐引用方式 GB/T 7714 | Wei Zhao,Jia Zhu,Qiang Qu,et al. Task-oriented keyphrase extraction from social media[J]. Multimedia Tools and Applications,2017. |
| APA | Wei Zhao,Jia Zhu,Qiang Qu,Wei Xu,YuZhi Liang,&Min Yang.(2017).Task-oriented keyphrase extraction from social media.Multimedia Tools and Applications. |
| MLA | Wei Zhao,et al."Task-oriented keyphrase extraction from social media".Multimedia Tools and Applications (2017). |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
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。