From To-CLIR: Web-based natural language interface for cross-language information retrieval

This paper describes the implementation of FromTo-CLIR, a Web-based natural language interface for cross-language information retrieval, which consists of four parts: query translator, meta-search engine, front-end and back-end processors, and a robust hybrid machine translator. A method is proposed...

Full description

Saved in:
Bibliographic Details
Published in:Information processing & management 1999-07, Vol.35 (4), p.559
Main Authors: Kim, Taewan, Chul-Min Sim, Yuh, Sanghwa, Jung, Hanmin
Format: Article
Language:English
Subjects:
Hypertext
Information retrieval
Natural language
Semantics
URLs
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes the implementation of FromTo-CLIR, a Web-based natural language interface for cross-language information retrieval, which consists of four parts: query translator, meta-search engine, front-end and back-end processors, and a robust hybrid machine translator. A method is proposed that uses a semantic category tree and collocation to resolve the ambiguity of query translation. The front-end and back-end processors are used in which domain identifier determines the domain of the retrieved documents, machine translators translate the retrieved documents and tag manager deals with the HTML tags to preserve the layout of the original Web document. To obtain a robust translation within the Web environment, a hybrid translation engine is used that combines a pattern-based module with a rule-based translator and includes pre- and post-fail softeners.
ISSN:0306-4573
1873-5371