Relevant Question Answering in Comminity Based Networks Using Deep LSTM Neural Networks
کد مقاله : 1235-CFIS (R1)
نویسندگان:
الهه کریمی *1، بابک مجیدی2، محمد تقی منظوری3
1دانشگاه خاتم،تهران،ایران
2گروه مهندسی کامپیوتر دانشگاه خاتم
3گروه مهندسی کامپیوتر دانشگاه صنعتی شریف
چکیده مقاله:
Community based Question Answering (CQA) websites enable users to post their questions and their questions will be answered by other users. These group of social networking websites are one of the most popular websites on the Internet. The responses on these CQA websites can be for specific questions related to a specific field of interest to the users or to all kind of questions. Creating automated CQA websites is of great interest for the natural language processing research. One of task in development of automated CQA websites is finding similar questions to the question asked by the user. In this paper, a novel method for finding questions relevant questions to the question of a user using deep LSTM neural networks is proposed. Experimental results show that the proposed algorithm has high accuracy for finding questions in CQA social networks.
کلیدواژه ها:
Social network, Community based question answering, recurrent neural networks, LSTM, deep learning.
وضعیت : مقاله برای ارائه شفاهی پذیرفته شده است
هفتمین کنگره مشترک سیستمهای فازی و هوشمند ایران