作者: M Yasukawa , F Scholer , J Culpepper
DOI:
关键词:
摘要: In this paper, we present a novel approach to language independent, ranked document retrieval using our new self-index search engine, Newt. To knowledge, is the first experimental study of self-indexing for multilingual Information Retrieval tasks. We evaluate query effectiveness indexes Japanese and English. explore impact that linguistic processing, stemming stopping have on character-aligned indexes, advantages challenges discovered during initial evaluation.