Untitled Document

Resources for English-Chinese CLIR

Doug Oard has a technical report on Resources for Chinese-English Cross-Language IR, which lists resources and tools on Encoding, character set, and Language identification, Character set conversion, segmentation and compound splitting, proper name, and mapping terms between languages. For each resource or tool, its availabilty, cost, format, domain coverage, size, and other information are provided. Here is the HTML version of his report.

In addition to the resources listed in Doug's report, I found the following resources that might be useful in English-Chinese CLIR. My intention is to find as many publicly available and free resources on the web as possible and make good use of them in CLIR research.

English-Chinese Bilingual Dictionary

Paul Denisowski's CEDICT

It was inspired by Jim Breen's Japanese-English EDICT.
Freely downloadable from http://www.mindspring.com/~paul_denisowski/cedict.html
Contains 23510 entries in 1 November 1998
Available in both GB and BIG5 character sets.

Yick Yam Lam's E-C bilingual dictionary

Freely downloadable from http://members.tripod.com/~super_ylam/Dictionary/dict.zip
contains about 76,000 entries.
Originally available in BIG5. I converted it to GB. You can find GB version here.
Evidently this dictionary was manually constructed and intended for human use. It has Part-Of-Speech tags for each entry and different translations listed under POS tags. Translation Examples are provided in some cases. It takes some time to convert it to machine readable format. I extracted a MRD using a small C program, which contains English words (or phrase), its POS and Chinese translations.

Eng-Chi

Downloadable from http://www.math.psu.edu/simpson/chinese/ChinText/b5/eng-chi (BIG5) http://www.math.psu.edu/simpson/chinese/ChinText/gb/eng-chi (GB)
contains 7720 entries. (not 103K as Doug claimed)

Online English-Chinese bilingual dictionaries

TigerNt
Online Eng-Chi bidirectional dictionary, GRE, TOFEL vocabulary

Technical terminology

E-C dictionary on computing and communications
term list with English computing terms and their corresponding Chinese translations
An intelligent database for standard Chinese computing terminology
online searchable database
An E-C IT glossary
available both in GB and BIG5.

Proper name resourses

Online proper name search from Taiwan
It includes translation for organizations, Asian person names and names of most famous people in the world.

English-Chinese Machine Translation Software

Free Online E-C Translation Service

MTIR English to Chinese web page translation service
Online free web page translation service provided by National Taiwan University.
Prominent Online words and sentences translation
Online English to Chinese words and sentences translation provided by Prominent Software Technology LTD. in Hong kong.

Commercial E-C MT software

Popular E-C MT softwares in Mainland China

TranStar

E-C bidirectional MT system. It claims to have 250,000 entries in their general dictionary. 15 specialty dictionaries with in total 500,000 entries. Trial version downloadable.

KingSoft

Bidirectional. 17,000,000 words in standard version. Has also Business and Economics version and Science and Technology version. Trial version downloadable.

Other MT systerms and their trial versions can be found here.

English-Chinese bilingual corpora

English-Chinese parallel texts collected by Wang Lixun available at http://web.bham.ac.uk/lxw715/EnglishChineseCorpus.html

Most are novels.