Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/112296
題名: | ICE: Item Concept Embedding via Textual Information | 作者: | 蔡銘峰 Wang, Chuan-Ju Wang, Ting-Hsiang Yang, Hsiu-Wei Chang, Bo-Sin Tsai, Ming-Feng |
貢獻者: | 資訊科學系 | 關鍵詞: | concept embedding; conceptual retrieval; information network; textual information | 日期: | Aug-2017 | 上傳時間: | 29-Aug-2017 | 摘要: | This paper proposes an item concept embedding (ICE) framework to model item concepts via textual information. Specifically, in the proposed framework there are two stages: graph construction and embedding learning. In the first stage, we propose a generalized network construction method to build a network involving heterogeneous nodes and a mixture of both homogeneous and heterogeneous relations. The second stage leverages the concept of neighborhood proximity to learn the embeddings of both items and words. With the proposed carefully designed ICE networks, the resulting embedding facilitates both homogeneous and heterogeneous retrieval, including item-to-item and word-to-item retrieval. Moreover, as a distributed embedding approach, the proposed ICE approach not only generates related retrieval results but also delivers more diverse results than traditional keyword-matching-based approaches. As our experiments on two real-world datasets show, ICE encodes useful textual information and thus outperforms traditional methods in various item classification and retrieval tasks. | 關聯: | Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pages 85-94 | 資料類型: | conference | DOI: | http://dx.doi.org/10.1145/3077136.3080807 |
Appears in Collections: | 會議論文 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
p85-wang.pdf | 1.54 MB | Adobe PDF2 | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.