Kiwi: a multilingual usage consultation tool based on internet searching

Authors:
Kumiko Tanaka-Ishii;Masato Yamamoto;Hiroshi Nakagawa
Affiliations:
The University of Tokyo;The University of Tokyo;The University of Tokyo
Venue:
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 2
Year:
2003

Citing 4
Cited 1

On the MSE robustness of batching estimators

Proceedings of the 33nd conference on Winter simulation
Using the web as a bilingual dictionary

DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
Using the web to overcome data sparseness

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
A simple but powerful automatic term extraction method

COMPUTERM '02 COLING-02 on COMPUTERM 2002: second international workshop on computational terminology - Volume 14

Extracting paraphrases of japanese action word of sentence ending part from web and mobile news articles

AIRS'04 Proceedings of the 2004 international conference on Asian Information Retrieval Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a usage consultation tool based on Internet searching. When a user enters a string of words that he wants to find the usage for, the system sends a query to the search engine to obtain a corpus about the string. The corpus is statistically analyzed and results are displayed. As the system uses neither language-dependent analysis nor initial data, queries can be made in any language, even languages for which there are no well-established analytical methods. Also, since the corpus is dynamically obtained from the search engines, the usages provided to the user are always up to date. Kiwi can fill in the missing parts of the collocations frequently used by native speakers.