초록

Abstract

Our limited understanding of real-life music information queries is an impediment to developing music information retrieval (MIR) systems that meet the needs of real users. This study aims to contribute to developing a theorized understanding of how people seek music information by an empirical investigation of real-life queries, in particular, focusing on the accuracy of user-provided information and users' uncertainty expressions. This study found that much of users' information is inaccurate; users made various syntactic and semantic errors in providing this information. Despite these inaccuracies and uncertainties, many queries were successful in eliciting correct answers. A theory from pragmatics is suggested as a partial explanation for the unexpected success of inaccurate queries.

초록

웹 문서 검색을 위해 키워드와 불리언 연산식을 사용하는 것에 비해 자연어 질의 문장을 입력하는 방법은 검색 시스템 사용자에게 훨씬 이상적인 인터페이스이다. 본 논문은 사용자가 입력하는 자연어 질의 문장을 구문 분석하고 그 구문 구조에 기반하여 검색어를 확장하는 다중 검색 기법을 제안한다. 구문 트리를 순회하여 구조적으로 연관된 복합 명사를 조합하거나 분할하는 과정을 거치고, 이형 표기 및 축약 표기 용어들에 대해 확장 다중 검색함으로써 웹 정보 검색 시스템의 재현율과 정확도를 높일 수 있다.

Abstract

For the users of information retrieval systems, natural language query is the more ideal interface, compared with keyword and boolean expressions. This paper proposes a retrieval technique with expanded keyword from syntactically-analyzed structures of natural language query as user input. Through the steps combining or splitting the compound nouns based on syntactic tree traversal of the query, and expanding the other-formed or shorten-formed into multiple keyword, it can enhance the precision and correctness of the retrieval system.