초록

용어보기논문에서 용어와 풀이말을 자동 추출한 결과로, 시범 서비스 중입니다. AI-Helper

Abstract ▼ AI-Helper

Identifying user's question into several topics helps respondents answering the question in a cQA service. Since it affects the overall performance directly, most of the cQA services have a topic recommendation function. For this function, automatically topic identification method is required. The c...

Identifying user's question into several topics helps respondents answering the question in a cQA service. Since it affects the overall performance directly, most of the cQA services have a topic recommendation function. For this function, automatically topic identification method is required. The cQA service has the structural features of the question-answer pairs that consist of the title of question, the body of question and the answer. The word has a different distribution in each structural area (title, body, answer). In this paper, we propose a novel effective word weighting method based on language model using the structural features in the cQA service for automatic topic identification. We calculate the topic-based occurrence probability of a word in each structure area. As a result, the proposed method shows significant improvement in our experiment.

주제어