@inproceedings{cf25be36d4214adc970f28dffc610f1a,
title = "Event Source Page Discovery via Policy-Based RL with Multi-task Neural Sequence Model",
abstract = "The problem of finding event announcement pages for any given website is called event source page discovery. In this paper, we show a policy-based deep reinforcement learning (RL) model for the event source page discovery agent. We use two stages to train our agent, pre-training and fine-tuning. In the pre-training phase, the model is trained with limited labeled data, where each episode has a fixed number of steps. In the fine-tuning phase, the agent is trained using unlabeled data and a reward system based on an event source page classifier. The agent learns whether to continue exploring or stop exploring through an adaptive threshold. The proposed agent achieves 74% precision with a 1.28 unit cost (the average number of clicks for each event source page) on the real word data set.",
keywords = "Event source page discovery, Multi-task neural model, Reinforcement learning, Web mining",
author = "Chang, {Chia Hui} and Liao, {Yu Ching} and Ting Yeh",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 23rd International Conference on Web Information Systems Engineering, WISE 2021 ; Conference date: 01-11-2022 Through 03-11-2022",
year = "2022",
doi = "10.1007/978-3-031-20891-1_42",
language = "???core.languages.en_GB???",
isbn = "9783031208904",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "597--606",
editor = "Richard Chbeir and Helen Huang and Fabrizio Silvestri and Yannis Manolopoulos and Yanchun Zhang and Yanchun Zhang",
booktitle = "Web Information Systems Engineering – WISE 2022 - 23rd International Conference, Proceedings",
}