Abdul Majid Bhurgri Institute of Language Engineering

AMBILE is an autonomous language-technology institute of the Government of Sindh, named after the pioneer of Sindhi computing Abdul-Majid Bhurgri.AMBILE 是信德省政府下属的语言技术自治机构，以信德语计算先驱阿卜杜勒-马吉德·布尔格里命名。

It operates under the Culture, Tourism, Antiquities and Archives Department and works on computational processing and natural language processing for the Sindhi language.该机构隶属于文化、旅游、文物与档案部，致力于信德语的计算处理与自然语言处理。

The institute develops lexical databases, optical character recognition software, fonts, transliteration tools and artificial-intelligence datasets, and releases most of them as free web or desktop resources.机构开发词汇数据库、光学字符识别软件、字体、转写工具与人工智能数据集，其中多数以免费网页或桌面资源的形式发布。

It is based behind the Sindh Museum on the N-5 highway in Qasimabad, Hyderabad, and holds ISO 9001:2015 certification for its quality-management system.机构位于海得拉巴卡西马巴德 N-5 国道旁的信德博物馆后方，其质量管理体系持有 ISO 9001:2015 认证。

History

• The idea originated in a briefing by language engineer Amar Fayaz Buriro to culture minister Syed Sardar Ali Shah on 18 August 2016 during a visit to the Sindhi Language Authority.这一构想源于语言工程师阿马尔·法亚兹·布罗 2016 年 8 月 18 日访问信德语管理局时向文化部长赛义德·萨尔达尔·阿里·沙阿所作的汇报。
• The minister announced the institute in 2017, and the provincial government added the scheme to its development budget for the 2017-18 fiscal year.部长于 2017 年宣布成立该机构，省政府随后把这一方案列入 2017-18 财年的发展预算。
• The institute's own timeline dates the foundation of its building to 2018 and its inauguration to 2019, with project work beginning in 2020.机构自己的时间线把大楼奠基定在 2018 年，把正式启用定在 2019 年，项目工作则从 2020 年开始。
• It is named after Abdul-Majid Bhurgri, whom the provincial government credits as the founder of Sindhi computing.机构以阿卜杜勒-马吉德·布尔格里命名，省政府把他视为信德语计算的奠基人。
• Bhurgri had coordinated with Microsoft on Unicode-based Perso-Arabic support for Sindhi around 2001, work that helped standardise the script on modern computers.布尔格里曾在 2001 年前后与微软合作开发基于 Unicode 的信德语波斯-阿拉伯字母支持，这项工作推动了该文字在现代计算机上的标准化。
• The Sindh Assembly gave the institute a statutory basis in the Abdul Majid Bhurgri Institute of Language Engineering Act, 2019, published as Sindh Act No. XVI of 2021.信德省议会通过 2019 年《阿卜杜勒·马吉德·布尔格里语言工程学院法》赋予机构法定地位，该法以 2021 年信德省第十六号法案公布。
• The Act defines the institute as an autonomous body under the culture department and sets out its mandate to standardise Sindhi computing and voice synthesis.该法把机构界定为文化部下属的自治单位，并规定其职责包括规范信德语的计算处理与语音合成。
• It also authorises automatic translation and transliteration, online portals for Sindhi literature, and the localisation of mobile technology, robotics and artificial intelligence.法案还授权机构开展自动翻译与转写、建设信德语文学在线门户，并推动移动技术、机器人与人工智能的信德语本地化。
• The institute is required to train language-engineering professionals and to build a consortium of national and international stakeholders working on the language.机构有义务培训语言工程专业人才，并联合国内外从事信德语工作的利益相关方组成联盟。
• Its early work concentrated on the Sindhi WordNet lexical database and on digitising Sindhi texts that existed only in print or in legacy fonts.机构早期的工作集中在信德语 WordNet 词汇数据库，以及把仅以印刷体或旧字体存在的信德语文本数字化。
• In 2022 it formally launched the AMBILE Hamiz Ali Sindhi OCR system, which converts scanned Sindhi documents into editable text.2022 年，机构正式发布 AMBILE Hamiz Ali 信德语光学字符识别系统，可把扫描的信德语文档转换为可编辑文本。
• The institute later released the Bhittaipedia portal, which presents the poetry of Shah Abdul Latif Bhittai with machine translation, transliteration and lexical analysis.机构随后推出 Bhittaipedia 门户，以机器翻译、转写与词汇分析呈现沙阿·阿卜杜勒·拉蒂夫·比泰的诗歌。
• In April 2026 its director Amar Fayaz Buriro advised the Sindh Textbook Board on converting textbook content into a text-centric, machine-readable format.2026 年 4 月，机构主任阿马尔·法亚兹·布罗向信德教科书委员会提出建议，把教科书内容改造为以文本为中心、可供机器读取的格式。
• By September 2026 the institute was receiving provincial culture secretaries and expanding its collaborations with universities and literary organisations.到 2026 年 9 月，机构已接待省文化部门负责人，并不断扩大与高校及文学组织的合作。
• The institute's timeline places its first project work in 2020, the year after its inauguration, when the WordNet and OCR programmes moved from planning into development.机构的时间线把首批项目工作定在启用后的 2020 年，当时 WordNet 与光学字符识别项目从规划转入开发。
• Its website describes the Act as the legal basis for functions that range from standardising voice synthesis to publishing research completed at the institute.机构网站把该法列为其职权依据，职责范围从规范语音合成一直延伸到发表机构完成的研究成果。

Mission and activities

• The Sindhi WordNet is a lexical database that groups words into synonym sets and records semantic relations for word-sense disambiguation, information retrieval and machine translation.信德语 WordNet 是一个词汇数据库，把词语归入同义词集合并记录语义关系，用于词义消歧、信息检索与机器翻译。
• The AMBILE Hamiz Ali Sindhi OCR is a Windows application that converts scanned Sindhi text into editable text and supports 62 different Sindhi fonts.AMBILE Hamiz Ali 信德语光学字符识别是一款 Windows 应用，可把扫描的信德语文本转换为可编辑文本，并支持 62 种信德语字体。
• The OCR requires images of at least 300 DPI and works offline after installation, which suits publishers, educational institutions and researchers who handle printed Sindhi material.该识别软件要求图像分辨率至少达到 300 DPI，安装后可离线运行，适合处理纸质信德语材料的出版社、教育机构与研究人员。
• Bhittaipedia offers the verses of Shah Abdul Latif Bhittai with machine translations into 130 languages, transliteration and a word-by-word dictionary.Bhittaipedia 提供沙阿·阿卜杜勒·拉蒂夫·比泰的诗句，配有 130 种语言的机器翻译、转写以及逐词词典。
• Shah Jo Kosh is a dictionary of the Shah Jo Risalo that records synonyms, antonyms, etymology, grammatical parsing and the verses in which each word appears.Shah Jo Kosh 是一部《沙阿诗集》词典，记录同义词、反义词、词源、语法分析以及每个词出现的诗句。
• The institute's Sindhi converters include Hesudhar for orthographic correction and a Unicode converter for text composed before Unicode was adopted.机构的信德语转换工具包括用于字形校正的 Hesudhar，以及把 Unicode 采用前编排的文本转为标准编码的转换器。
• An E. Trumpp converter maps modern Sindhi typography to the nineteenth-century type used for the first printed edition of the Risalo.一个 E. Trumpp 转换器可把现代信德语字体映射到十九世纪首次印刷《沙阿诗集》时使用的字体。
• The Girdan Developer generates derivations from a Sindhi verb root, and the institute also offers a Sindhi-language calculator and a Desi calendar converter.Girdan 派生工具可从信德语动词词根生成完整派生树，机构还提供信德语计算器与德西历转换器。
• Its speech programme is at an alpha stage, with separate Sindhi text-to-speech and speech-to-text prototypes released for testing and research.机构的语音项目仍处于内部测试阶段，分别发布了信德语文本转语音与语音转文本原型，供测试与研究使用。
• The team estimates that production-quality speech systems need more than 50 million voice segments for each major Sindhi dialect.团队估计，要达到生产级质量，每种主要信德语方言都需要超过五千万条语音片段。
• The IVC Script Font covers symbols of the Indus Valley script, while the AMBILE Multilingual Font supports most Arabic-Perso-based languages.印度河流域文明文字字体收录该古代文字的符号，而 AMBILE 多语言字体支持大多数基于阿拉伯-波斯字母的语言。
• The institute maintains the Culture Department E-Library and the Sindhi Language Authority Library as web platforms for books and audio-visual material.机构维护文化部电子图书馆与信德语管理局图书馆两个网络平台，提供图书与音视频资料。
• The homepage brands its artificial-intelligence programme as SINDH.AI and describes it as an effort to power Sindhi in the age of AI.机构网站在 SINDH.AI 品牌下展示其人工智能计划，称其目标是在人工智能时代为信德语提供技术支撑。
• Bhittaipedia also includes lexical-density analysis and transliteration alongside translation, according to the institute's project description.根据机构的项目说明，Bhittaipedia 除翻译外还提供词汇密度分析与转写。
• The institute provides technical advice to public institutions, as shown by its 2026 proposal to rebuild the Sindh Textbook Board portal around structured text and an offline mobile application.机构向公共机构提供技术咨询，2026 年围绕结构化文本与离线移动应用改造信德教科书委员会门户的建议即为一例。

Organization and governance

• AMBILE is an autonomous government body rather than a company, and its chairman is the provincial culture minister Syed Zulfiqar Ali Shah.AMBILE 是政府自治机构而非公司，主席由省文化部长赛义德·祖勒菲卡尔·阿里·沙阿担任。
• Abdul-Majid Bhurgri holds the title of Lifetime Co-Chairman, and the culture secretary Khair Muhammad Kalwar sits on the board.阿卜杜勒-马吉德·布尔格里担任终身联合主席，文化秘书海尔·穆罕默德·卡尔瓦尔为董事会成员。
• Amar Fayaz Buriro, a language engineer and linguist, serves as director and led the institute's creation from its conceptual stage.语言工程师与语言学家阿马尔·法亚兹·布罗担任主任，并从构想阶段起主导机构的创建。
• The institute reports to the Culture, Tourism, Antiquities and Archives Department of the Government of Sindh.机构向信德省政府文化、旅游、文物与档案部汇报工作。
• It holds ISO 9001:2015 certification, which covers its research, software development and language-service processes.机构持有 ISO 9001:2015 认证，覆盖其研究、软件开发与语言服务流程。
• Its office is behind the Sindh Museum and the Sindhi Language Authority on the N-5 highway in Qasimabad, Hyderabad.机构办公室位于海得拉巴卡西马巴德 N-5 国道旁，地处信德博物馆与信德语管理局后方。
• In 2025 it signed memoranda of understanding with Shaheed Benazir Bhutto University, XFlow Research, the Shah Abdul Latif Bhittai Chair at the University of Karachi and the University of Sindh.2025 年，机构与沙希德·贝娜齐尔·布托大学、XFlow Research、卡拉奇大学沙阿·阿卜杜勒·拉蒂夫·比泰讲席以及信德大学签署谅解备忘录。
• A further memorandum with the Sindhi Language Authority followed on 22 January 2026, while the XFlow Research agreement was terminated on 31 October 2025.机构又于 2026 年 1 月 22 日与信德语管理局签署谅解备忘录，而与 XFlow Research 的协议已于 2025 年 10 月 31 日终止。

Membership and funding

• AMBILE is publicly funded through the Government of Sindh and does not publish revenue, profit or a balance sheet.AMBILE 由信德省政府提供公共资金，不公布营收、利润或资产负债表。
• Its creation was financed as a provincial development scheme included in the 2017-18 budget.机构的创建作为省级发展方案获得拨款，并列入 2017-18 财年预算。
• The institute distributes its software and online tools free of charge, so licence sales are not a reported revenue source.机构免费分发软件与在线工具，软件许可销售并非其公布的收入来源。
• Its partnerships with universities and the textbook board are in-kind collaborations rather than commercial contracts.机构与高校及教科书委员会的合作属于实物协作，而非商业合同。
• Staff and infrastructure costs are borne through the culture department's budget rather than through service fees.人员与基础设施成本由文化部预算承担，而非通过服务收费弥补。
• The institute has not disclosed a separate endowment or annual operating budget on its website.机构未在网站上披露独立的捐赠基金或年度运营预算。
• Its ISO certification covers service and research processes rather than financial reporting.机构的 ISO 认证覆盖服务与研究流程，并不涉及财务报告。
• The institute's tools are delivered through public websites, which keeps distribution costs low but leaves hosting dependent on provincial support.机构的工具通过公共网站分发，这降低了传播成本，但托管服务仍依赖省级财政支持。

Reception

• The provincial government presents the institute as the institutional home of Sindhi language engineering.省政府把该机构定位为信德语语言工程的机构化载体。
• Its OCR and WordNet tools are used by publishers, educational institutions and researchers working with Sindhi text.其光学字符识别与 WordNet 工具被处理信德语文本的出版社、教育机构与研究人员使用。
• In 2026 the Sindh Textbook Board invited the institute to redesign its textbook portal around structured text, citing artificial-intelligence and accessibility benefits.2026 年，信德教科书委员会邀请机构围绕结构化文本重新设计教科书门户，并提到人工智能与无障碍方面的收益。
• The institute's director has argued that text-based educational content is more reliable for language models than image or PDF captures.机构主任主张，以文本为基础的教育内容比图像或 PDF 截取更适合语言模型使用。
• No independent ranking or consumer assessment of the institute was found, and its public record consists mainly of government and institutional notices.目前未发现针对该机构的独立排名或消费者评估，其公开记录主要由政府与机构公告构成。
• The 2026 textbook-portal proposal was presented to Sindh Textbook Board chairman Pervaiz Ahmed Baloch and secretary Nusrat Parveen Sahito after the technical meeting.2026 年的教科书门户方案在技术会议后提交给信德教科书委员会主席佩尔韦兹·艾哈迈德·巴洛赫与秘书努斯拉特·帕尔文·萨希托。

Notable people

• Abdul-Majid Bhurgri is honoured as the founder of Sindhi computing and serves as the institute's Lifetime Co-Chairman.阿卜杜勒-马吉德·布尔格里被尊为信德语计算的奠基人，并担任机构终身联合主席。
• Amar Fayaz Buriro proposed the institute, became its director and represents it in provincial education and language-technology meetings.阿马尔·法亚兹·布罗提出设立该机构，出任主任，并在省级教育与语言技术会议中代表机构。
• Syed Sardar Ali Shah, the culture minister in 2016 and 2017, announced the institute and backed its budget line.赛义德·萨尔达尔·阿里·沙阿在 2016 至 2017 年担任文化部长，宣布成立机构并支持其预算项目。
• Syed Zulfiqar Ali Shah currently chairs the institute as culture minister, with Khair Muhammad Kalwar as board member and culture secretary.赛义德·祖勒菲卡尔·阿里·沙阿目前以文化部长身份担任机构主席，海尔·穆罕默德·卡尔瓦尔则以文化秘书身份担任董事会成员。