Researches

WebLEAP.... Web Language Evaluation Assistant Program

Abstract

  • WebLEAP aims to inform people of the existence and the popularity of expressions in the world. It gets an expression as input and returns the frequencies in Web documents of the word sequences extracted from the given expression by using a search engine. The expression and the frequencies are presented graphically so that the user can estimate the result easily and judge with more confidence.

Examples

  • In this example, "my self in times" should be "myself in times", and "mother mary come to" should be "mother Mary comes to". WebLEAP highlights any strange parts of the target phrase or sentence. Frequencies are shown in colored bars, so the user of WebLEAP can recognize these strange parts easily.

Key words

  • corpus, knowledge acquisition, web mining, web services, e-learning, natural language processing, language teaching

Our Picture

WebLEAP WebLEAP/WEB, WebLEAP on the Web and its manual by Yoshiaki Matsuda. WebLEAP/DSR, WebLEAP which is embedded in the DSR (Distributed System Recorder). DSR is a computer assisted teaching system for distributed systems. It can also be used as a benchmark test tool for distributed systems.

A Manual of the WebLEAP/DSR (in Japanese) DSR, Distributed System Recorder, (dsr.jar, updated 17 Apr. 2004) This includes the latest version of the WebLEAP/DSR. It can be used by the following steps. Install the J2SE or JRE. It can be obtained from java.sun.com. Down load this (dsr.jar). Add the java command path to the "path". for example in the Windows OS, if the J2SE is installed at "c:\j2sdk1.4.2_02", then, do the "set path=%path%;c:\j2sdk1.4.2_02\bin" in the command window. jar -xvf dsr.jar The command "jar xvf .jar" extracts all files in the .jar. You can also extract the same files by downloading dsr.zip, and unzipping this zip file. cd dsr Change directory to the dsr which is extracted by the previous procedure. java -cp classes:lib application.webleap.WebLEAPFrame WebLEAP/DSR is started by this command. FAQ on WebLEAP Please use the WebLEAP at your own risk. We are improving the WebLEAP now. We welcome your suggestions, requests, comments.

Papers on the WebLEAP

  • Takashi Yamanoue. Toshiro Minami, Ian Ruxton, Wataru Sakurai: "Learning Usage of English KWICly with WebLEAP/DSR" Proceedings of the 2nd International Conference on Information Technology and Applications (ICITA-2004), 14-6, Harbin, China, January. 8-11, 2004.
  • Takashi Yamanoue. Toshiro Minami, Ian Ruxton: Web-Based Concordancer to Learn Usage of English Expressions, Proceedings of the 1st International Conference on Information Technology and Applications (ICITA-2002), Bathurst, Australia, Nov. 25-29, 2002. Abstract, Full paper, Presentation.
  • Takashi Yamanoue, Toshiro Minami and Ian Ruxton: A WWW Concordancer to Assist in the Writing of Documents Proc. Foundation of Software Engineering Workshop (FOSE 2000), Kindai Kagakusha, pp213-220, Jan. 2001.
  • Takashi Yamanoue, Toshiro Minami and Ian Ruxton: Using the WebLEAP(Web Language Evaluation Assistant Program) to Write English Composition, FLEAT IV, The Fourth Conference on Foreign Language Education and Technology-July 28 to August 1,2000,
  • Takashi Yamanoue, Toshiro Minami and Ian Ruxton: A Writer's Assistant based on the World Wide Web-Knowledge, Proceedings of the Fourth Australian Knowledge Acquisition Wrokshop, in conjunction with the Twelfth Joint Conference on Artifitial Intelligence, AI'99 , pp.1-12, Sydney, Australia-December 5-6 1999
    • Abstract: Finding the most suitable expression in writing is quite hard especially for those who write in their second language. The hardest task is to judge whether the expressions at hand are suitable or not. This paper introduces a system that aims to inform people of the existence and the popularity of expressions in the world. It gets an expression as input and returns the frequencies in Web documents of the word sequences extracted from the given expression by using a search engine. The expression and the numbers are presented graphically so that the user can estimate the result easily and judge with more confidence. We demonstrate its usefulness by illustrating several experiments to find suitable expressions, solving some questions and writing this paper itself. From these experiments, we conclude that such a system has high potential and will become an indispensable tool for all writers in the future.

Slides and talk of the presentation Power point file of the presentation

References, Related links, Web corpuses, other Knowledge Acquisition Systems, etc.

tools, concordances

  • Linguistic Computing Resources on the Internet, SIL
  • Satoh, H., "Kwic On AltaVista?", etc.
  • Research and Development Unit for English Studies, University of Liverpool :WebCorp?
  • openNLP,a Java API for natural language components
  • Corpus Project��Ϣ�ġ���
  • SARA
  • TXTANA
  • Ushijima, K., Suganuma, A. et al.: The Writing Tool for Japanese Documents ``SUIKOU", Iwanami Software Library, Iwanami, 1993. (in Japanese)
  • WordSmith? Tools
  • MicroConcord?

Tools for learning english

  • Simple Concordance Program
  • Corpuses, Search engines, etc.
  • AltaVista?
  • Locos
  • google
  • Yahoo
  • British National Corpus
  • ICAME

Groups,Communities, Academic societies, People, etc.

  • Japan Association for English Corpus Studies(�Ѹ쥳���ѥ��ز�)
  • NL(������������������), IPSJ(���������ز�),japan
  • FLEAT IV, Fourth International Conference on Foreign Language Education Nagoya University Corpus Project ���������ش�Ϣ���浡��WWW�ڡ����ꥹ�� , by �������ظ�ƣ���� �����˴ؤ����ڡ���
  • Masatoshi Tabuki at kyushu institute of technology, corpus
  • Keiji Konomi at kyushu institute of technology, corpus
  • Naoyuki Okada, Professor Emeritus, Kyushu Institute of Technology, AI and language
  • Soap, google
  • Google Web APIs
    • Google Outlie Browser
    • CapeSpeller?
    • Mail 2 Google

Others

  • Kazuaki Ando, Yuichi Tsunashima, Masashi Okada, A Writing Support Tool for Learners of English and/or Japanese as a Second Language, AACE, World conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA) 2008, Vienna, Austria June 30, 2008 They refer our paper. Thank you for them.
  • Marianne Hundt, Nadja Nesselhauf Corpus Linguistics and the Web , Editions Rodopi BV (December 20, 2006) They refer our paper. Thank you for them.
  • Murakami, M.; Kimura, M.; Honda, N. Development of a New Corpus System for English Writing Support and its Fundamental Study , Fuzzy Systems, 2006 IEEE International Conference on Volume , Issue , July 16-21, 2006 Page(s): 2090 - 2096 Digital Object Identifier 10.1109/FUZZY.2006.1681990 They refer our paper. Thank you for them.
  • Alphabit.net , a cura di Isabella Chiari This page has the link to our webleap page. Thank you, Isabella.
  • Satoshi Ono, Mari Jingushi, Shigeru Nakayama: Palindrome Generation based on Web Search Engine , Hinokuni Jyoho Symposium 2005, B-4-2, Iizuka, 7-8 March 2005. They refer our paper. Thank you for them.
  • Hironori Ohga: Constructing an English Writing Assistant System Using a Search Enginge, Master degree thesis of the graduate school of Waseda University, feb. 2005. (in Japanese) He refers our paper. Thank you, Mr. Ohga.
  • Keiichiro Moriyama: A study on search methods using the Google API , BA degree thesis of the department of liberal arts and information science, Ohtani University, 2005. He refers our paper. Thank you, Mr. Moriyama.
  • William H.Fletcher: Towards an Independent Search Engine for linguists: Issues and Solutions, "La Rete come Corpus", Forli 14 January 2005 He refers our paper. Thank you William.
  • Carlos Chesnevar, Ana Maguitman: An Argumentative Approach to Assessing Natural Language Usage based on the Web Corpus, Proceedings. of the European Conference on Artificial Intelligence (ECAI) 2004. Valencia, Spain, August 2004. They refer our paper. Thank you Carlos and Ana.
  • Masahiro Shibata, Yoichi Tomiura, Shosaku Tanaka: A Method for Retrieving Translations of Collocation in Web Data, Asian Symposium on Natural Language Processing to Overcome Language Barriers, Hainan Island, China, March 25-26, 2004, International Communications Limited: TOEIC Test Experience Kit, University COOP Union, 1999.(in Japanese)
  • Kudo, I. and Inoue, N.: Co-Occurrence Knowledge Acquisition from Corpora and Its Application, Journal of Japanese Society for Artificial Intelligence, Vol. 10, No. 2, pp.205-212, 1995. (in Japanese)
  • Takashi Yamanoue: A program which tries to win "Janken" game
  • John McCarthy?, A Professor of Stanford University, Lisp, Circumscription, Commonsense Reasoning, approximation logic, etc. ��ϩ����, �ⶶ����, ��������, ������: ���ֻظ��ξ�������, ��¤�������Ӹ�����ˡ, ���������ز���ʸ��, Vol.41, No.7, pp.1987-1998, 2000.
  • Seiji Yokoji, Katsumi Takahashi, Nobuyuki Miura, Ken-ichi Shima: Location Oriented Information Collection, Structuring and Retrieval, IPSJ Journal, Vol.41, No.7, pp.1987-1998, 2000. ��ƣ����: ����ɥ磻�ɥ����֤����Ѥ�������õ��, ���������ز���ʸ��, Vol.42, No.1, pp.-, 2001.
  • Satoshi Sato: Address Search on the World Wide Web IPSJ Journal Vol.42, No.1, pp.-, 2001. Kevin Knight: Mining Online Text, Communications of the ACM, November 1999-Volume 42, No.11, pp.58-61,1999.
  • Saito, T., Nakamura, J. and Akano, I.(Eds.): English Corpus Linguistics, Kenkyuusya Syuppan, 1998. (in Japanese)
  • M. Sharples, J. Goodlet and L. Pemberton: Developing a Writer's Assistant, In J. Hartley (ed.) Technology and Writing: Readings in the Psychology of Written Communication. London: Jessica Kingsley, 209-220. 1992.
  • Takaie, H. and Suga, H.: Practical Corpus Linguistics, Kirihara Yuni, 1998. (in Japanese)
  • The Official TOEIC Home Page
  • TOEIC Home Page(japanese)
  • James H. M. Webb: 121 Common Mistakes of Japanese Students of English(revised edition), The Japan Times,1991.
  • KAW -Knowledge Acquisition/Modelling/Management mailing list

takashi yamanoue, yamanoue@cc.kagoshima-u.ac.jp


Counter: 1189, today: 1, yesterday: 2

トップ   編集 凍結 差分 バックアップ 添付 複製 名前変更 リロード   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS
Last-modified: 2017-02-17 (金) 13:43:57 (1074d)