DETAILED PRODUCT LIST

 

CiyaTranTM

MT Machine Translation Engines, English (to/from) Farsi, Dari, Pashto and Arabic

Product Code

Direction and Supported Language(s)

Update History (Versions)

Price Range Based on Platform and Extensions

1001

English to Farsi

1.X, 2.X, 6.X, 7.X, 9.X

$990 to $8,900

1002

Farsi to English

1.X, 2.X, 6.X, 7.X, 9.X

Contact

1003

Dari Support: For 1002 and 1001

3.X, 5.X

Currently Unavailable

1004

Pashto Bidirectional

1.X, 2.X, 5.X, 6.X

Version-Dependent

1005

English to Farsi/Dari

3.X, 2.X, 9.X

Currently Unavailable

1006

Farsi/Dari to English

3.X, 2.X, 9.X

Contact

1007

English/Farsi/Dari Bidirectional

1.X, 3.X, 7.X, 9.X

$1,990 to $18,900

1008

Arabic English

1.X, 2.X

Contact

1009

English Arabic

1.X, 2.X

Contact

1010

English/Arabic Bidirectional

2.X, 3.X

$990 to $7,900

1100

MT Preprocessor

For MT V 5.X and above

$1,290 to $1,900

 

 

MT Engine Components

Product Code

Description

Price Range

Sentence/Fragment Segmentation Support: Separate sentences or sentence fragments that are independent of the neighboring sentence, sentence fragment or title

2001

English

Contact

2002

Farsi/Dari

Contact

2101

Word Segmentation Support: Space is not always present as a word separator in Farsi, Dari, Pashto and Arabic.

Contact

Morphological Analyzer

2202

English

Contact

2203

Farsi/Dari

Contact

2204

Pashto

Contact

Syntactical Analyzer (Tokenizing/Tagging)

2301

English

Contact

2302

Farsi

Contact

2303

Dari

Contact

2304

Pashto

Contact

Pattern and Production Support: Identify such patterns as numerals, dates, time, titles, enumerations, itemizations, adverb, adjective and verb formation, etc. Production use databases of grammatical models represented mathematically to simplify sentence structures.

2401

English

Contact

2402

Farsi/Dari

Contact

2403

Arabic

Contact

2404

Pashto

Contact

2511

English Affix Support: Prefix, suffix and infix meaning builder for Farsi/ Dari.

Contact

2521

Farsi Affix Support: Prefix, suffix and infix meaning builder for English.

Contact

2522

Farsi Verbal Form Disintegrator: ( ی )

Contact

2601

Translation Memory Support Module (Within Personal Dictionary)

Contact

 

 

MT Test Tools

Product Code

Description

Price Range

Static Regression Test: Software for intelligent comparison between a static database of sentences with known correct translation against a dynamic database of the same sentences with translation after each successive change to the MTs engine or databases. Contents of the static database are manually maintained.

3001

English to Farsi/Dari

Contact

3002

Farsi/Dari to English

Contact

3101

Database Automatic RVU: Series of utilities that check for and try to correct (or report) inconsistencies among various fields of the databases.

Contact

Sentence Generator (SenGen): Create trillions of different sentences and their correct translations to be used for testing bidirectional MT. SenGen should be used in conjunction with batch processor (4901). The count and type of sentences generated by SenGen is determined by the criteria set the user.

3201

English to Farsi

Contact

3202

Farsi to English

Contact

3203

English to Dari

Contact

3204

Dari to English

Contact

3205

English to Pashto

Contact

3206

Pashto to English

Contact

3301

Simulation: Combination of SenGen and Batch Processor that would allow automatic testing of billions of sentences that meet certain criteria.

Contact

 

 

MT Engine and Database Development Tools

Product Code

Description

Price Range

Statistical Analysis Support

4001

Data Collection: Collect data from the WEB, emails, and other electronic means, determine the Language, format, do the necessary format conversions, remove duplicate files, maintain frequencies.

Contact

4002

Data Organizer: Take the output of 4001, organize and generate reports and create derivative databases.

Contact

4101

Farsi Spelling Checker

Contact

Morph Converters

4201

Farsi to Finglish: ( ketab)

Contact

4202

English to Pinglish: (book )(John ) Used for proper noun generation.

Contact

4203

Formal Farsi to Slang Farsi: (ی <> ی )

Contact

4204

Slang Farsi to Slang Finglish: (ی miram)

Contact

Character Base Converter

4301

Finglish to Farsi: (ketab <> )

Contact

4302

Pinglish to English: ( <> book)

Contact

4303

Slang to Formal Farsi: (ی <> ی )

Contact

4304

Slang Finglish to Slang Farsi: (miram <> ی )

Contact

4321

Encoding Converter and Unification

Contact

Search tools: For search MT engines, search engines and MT development

4501

Farsi/Dari/Pashto/Arabic to Finglish Conversion, AKA Romanization

Contact

4502

English to Pinglish Conversion: AKA transliteration

Contact

Document Analysis Support Module (Pre-tokenization)

4701

Text Statistical Analysis: Text came from OCR, ASR; text type: dialogue, informal letter, newspaper article, technical documentation,

Contact

4702

File Type Detection (Text or image, compressed, encrypted, )

Contact

4703

File Format Determination (PDF, DOC, RTF, ) and Conversion

Contact

4705

Language Determination (English, German, , Farsi, Arabic, )

Contact

4706

English Determination (British/American), when input is English

Contact

4707

Translatability Determination: Based on the number of errors in spelling, punctuation, grammar, etc.

Contact

4708

Finglish to Farsi Conversion using 9105 and 9107

Contact

4709

Pinglish to English Conversion using 9404

Contact

4710

Slang to Farsi Conversion using 9106

Contact

4720

Morph Unification: Add space when it is missing, remove space when not needed; unify half-space, Invisible space, break space; unify encoding.

Contact

4730

Spell Checking and Correction using 9101, 9110 and 9109

Contact

4740

Domain Determination using 9302

Contact

4750

Extraction of Proverbs, Poetry and quotes from Quran using 9501, 9502 and 9503

Contact

4801

Pre-Translation Summarization for Farsi/Dari: When summarization is done in the source language, most of the meanings and concepts are preserved, as opposed to summarization after translation.

Contact

4901

Batch Processor: Collect files, convert and translate automatically.

Contact

 

 

MT, OCR and Miscellaneous Support Databases (Farsi, Dari, Arabic and Pashto)

Product Code

Description

Price Range

9101

Short List: Based on Amid Farsi to Farsi dictionary: 60,000 words with Root Language, Usage Frequency, Parts of Speech, primarily used for Farsi spell checking.

Contact

9102

Most-frequently-used words and phrases: 2,850,000 entries with Frequency, Parts of Speech

Contact

9103

Farsi words in English database: Farsi words needed to describe all the words in English. This database is used to optimize coding for Farsi support unit in an English to Farsi MT, since not all Farsi words are needed to describe all English words.

Contact

9104

Farsi to English Database: Designed and optimized for MT use with 1,740,000 entries

$7,900

9105

Finglish Database of most frequently used words and phrases: Farsi words transliterated in English alphabet, the method used in emails and some WEB sites where Farsi fonts and keyboard is not available to the O/S or the application.

Contact

9106

Slang Database of most frequently-used-words and verbal forms with formal (non-slang) equivalents

Contact

9107

Slang Finglish: Same as 9106 with Latin alphabet

Contact

9108

Proper Nouns (Farsi to English): Over 1,000,000 proper names, cities, places, landmarks, etc. (Pinglish is used for entries with non-Farsi source, such as Western names; and Finglish is used for entries with Farsi sources.) There may be more than one equivalent regardless of the source.

$1,900

9109

Words affected by absence of vowels: Fuzzy Logic links and phrasal forms are used to resolve ambiguities.

Contact

9110

Frequently misspelled words: Also, words that have more than one spelling with the same meaning.

Contact

9301

English to Farsi Database: Designed and optimized for MT use with 1,500,000 entries

Contact

9302

Domain-Specific Databases: Over 79 separate databases for Terminology Management Support Unit

$3,400

9403

English words in Farsi database: English words needed to describe all the words in Farsi. This database is used to optimize coding for English support unit in a Farsi to English MT, since not all English words are needed to describe all Farsi words.

Contact

9404

Pinglish Database of most frequently used words: English words transliterated using Farsi alphabet, the main solution when dealing with non-Farsi proper nouns, or action verbs or adjectives for which there is no good Farsi equivalent such as new computer-related technical terms or newly created terms in the medical or pharmaceutical fields.

Contact

9405

Proper Nouns (English to Farsi): Same as 9108 sorted in English.

Contact

9406

Acronyms: Over 100,000 English acronyms in 70 categories. Some categories such as military contain over 15,000 acronyms used by the US DoD.

Contact

Specific Domains

9501

Quran: In Arabic readily convertible to Finglish using 4201. This database is needed to quickly separate and tag quran quote, as they occur frequently in text.

Contact

9502

Poetry: Poetry is present frequently in Farsi text. This database is needed to quickly find and tag them, instead of trying to translate.

Contact

9503

Proverbs: Farsi proverb is present frequently in Farsi text. This database is needed to quickly find and tag them, instead of trying to translate them.

Contact

9601

Dari: Same as 9104 (Dari to English)

$7,900

9701

Pashto: Same as 9104 (Pashto to English)

$12,900

5101

Farsi specialized database for OCR

Contact

5102

OCR database of connected shapes

Contact

Miscellaneous Domains: Farsi/Dari/Arabic/Pashto/Finglish/Pinglish/Transliterated

9800

Complete list of 2,000 largest companies in the world

Contact

9802

Complete list of Embassies in the world with City name and country name

Contact

9803

Complete list of US Counties

Contact

9804

Complete list of US Cities

Contact

9805

Complete list of US Zip Codes

Contact

9806

Complete list of every Cities in the world

Contact

9807

Complete list of Airports in the world

Contact

9807

Complete list of Airlines in the world

Contact

9808

Over 200,000 proper names. The list includes Farsi, Arabic, Pashto, Dari, Western, Russian, Asian with variation spellings

Contact

9809

List of terrorist organizations

Contact

9810

List of World currencies

Contact

9810

List of World languages

Contact

9810

Complete list of Banks in the world

Contact

9810

Complete list of Cruise Lines in the World

Contact

9810

Complete list of world Museums

Contact

9810

Complete list of World Tallest Buildings

Contact

9810

Complete list of world Universities

Contact

9810

Complete list of oil & gas storage facilities in the world

Contact

9810

Complete list of Ports of the world

Contact

 

 

Printed Farsi (Dari), Arabic, Pashto, Urdu OCR Engines with diacritics support

Product Code

Supported Language

Description

Price Range

6001

Arabic

Arabic OCR

$1,390

6002

Farsi

Farsi OCR

$900

6003

Dari

Dari OCR

$900

6004

Pashto

Pashto OCR

$900

6005

Urdu

Urdu OCR

$900

 

 

Handwriting OCR

Product Code

Supported Language

Description

Price Range

6501

Arabic

Arabic OCR

Contact

6502

Farsi/Dari

Farsi OCR

$1,900

 

 

Miscellaneous

Product Code

Description

Price Range

Concept-Based Data Search: Search engine that finds text in Farsi, Arabic, Pashto and Dari with or without diacritics, with morphological analysis, encoding unification and transliteration and vowelization support. Supports over 100,000 proper names and other proper nouns such as geographical names.

4801

Farsi/Dari

Contact

4802

Pashto

Contact

4803

Arabic

Contact

4704

Mixed File Splitter: Separate portions of the input file that are not text and/or are in more than one language.

Contact

7001

DIEPTM (Digital Image Enhancement Processor)

$1,950 to $4,950

CiyaGateTM

7401

Farsi Only

$1,950 to $4,950

7402

Dari Only

$1,950 to $4,950

7403

Farsi and Dari Combined

$7,900 Full Version

7420

Pashto

$3,400 to $4,550

7450

Farsi, Dari and Pashto Combined

Contact