@inproceedings{6e0393b0e0d142deb772e96fe45154ab,
title = "應用興趣點辨識技術從 Web 中挖掘新商家資訊",
abstract = "This paper presents a system that could automatically extract new POIs from Web. First, we use special queries (e.g. Taipei+New Open) to find Web pages that might contain addresses for new stores. For web pages that contain addresses, we then apply store name recognition model to extract possible POIs. Finally, we train a model to find the most possible POI for the address found in the page. In this paper, we focus on POI name recognition and POI relation prediction. For POI recognition, we use store names from yellow pages as seed to prepare the training data via distant learning. Through entity selection and data processing, we obtain a model with 0.816 F1-measure as opposed to 0.432 F1-measure for a dictionary-based baseline. As for POI relation prediction, we compare three different strategies for negative example preparation. The best model could get 0.754 accuracy. We combine two POI recognition models with three classification models to test the overall performance. The best combination could extract 49 POIs every day with a single IP.",
keywords = "Address Recognition, POI Entity Recognition, POI Relation Prediction",
author = "Hsu, {Kuo Hsin} and Chuang, {Hsiu Min} and Chou, {Chien Lung} and Chang, {Chia Hui}",
note = "Publisher Copyright: {\textcopyright} The Association for Computational Linguistics and Chinese Language Processing; 29th Conference on Computational Linguistics and Speech Processing, ROCLING 2017 ; Conference date: 27-11-2017 Through 28-11-2017",
year = "2017",
month = nov,
day = "1",
language = "繁體中文",
series = "Proceedings of the 29th Conference on Computational Linguistics and Speech Processing, ROCLING 2017",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
pages = "53--67",
editor = "Lun-Wei Ku and Yu Tsao and Chi-Chun Lee and Cheng-Zen Yang and Hung-Yi Lee and Tsai, {Richard T.-H.} and Wen-Hsiang Lu and Shih-Hung Wu",
booktitle = "Proceedings of the 29th Conference on Computational Linguistics and Speech Processing, ROCLING 2017",
}