2023-10-30 –, Main program
(EN)
This session will share the methods, tools, and approaches on building knowledge graphs for underrepresented communities, for example, we will analyse the efforts made on the Quechua community, for instance, by building the Quechua Language and Knowledge Base (https://qichwa.wikibase.cloud/)
(ZH)
在本場次中我們將會分享為小眾社群創立知識圖譜的方法和工具；我們將會以奇楚亞社群為案例進行探討，如為奇楚亞社群建立專屬的語言和知識庫。(https://qichwa.wikibase.cloud/)
(EN)
The availability of interoperable linguistics resources is nowadays more urgent in order to save and help under-resourced languages, and their communities. Despite the efforts, not all languages are represented, nor made accessible in a structured format. Furthermore, well-spread languages, like English or Spanish, took up an overwhelming majority on the Web, while indigenous communities and their resources received less attention.
In order to overcome these limitations, we propose a methodology for creating knowledge graphs for under-resourced languages and their communities. By building knowledge graphs we allow the development of applications, the shaping of open educational resources, and the gathering of minority communities in a central space. For instance, we will show how to decentralize demographic contributions with Wikibase, which allows communities to design, create, curate and deploy a mature community-driven knowledge base. Furthermore, the Quechua Language and Knowledge Graph (https://qichwa.wikibase.cloud/) will be showcased. Finally, we will show how educators, students, researchers, and developers may work together for building inclusive applications and resources for all through knowledge graphs.
Session Outcomes
- Learn how to build a knowledge graph for an under-resourced language
- Know approaches and tools that can help to preserve indigenous language and knowledge.
- Advantages of building/creating knowledge graphs.
(ZH)
在現今的社會中，要拯救和幫助缺乏資源的語言及其社群，我們急需可交互工作的語言學資源。雖然有著來自多方的協助，但仍然有許多的語言尚未被記錄，更別說以結構化的形式向大眾公開。除此之外，強勢語言如英語或西班牙語佔據了網路上絕大部分的內容，而原住民及其資源則往往被忽略。
為了要克服這些限制，我們提出了一個為缺乏資源的語言和社群建立知識圖譜的方法。藉由建立知識圖譜，我們將能協助未來應用的發展、型塑開放教育資源、並將少數族群們凝聚起來。我們將會示範如何藉由 Wikibase 來擺脫人口中心化限制以做出貢獻，這將協助社群設計、建立、策畫、並設置一個成熟並由社群主導的知識庫。除此之外，我們也將會與各位分享奇楚亞語言和知識圖譜 (https://qichwa.wikibase.cloud/) 。最後我們將會展示，教師、學生、研究員、以及開發者們可以如何透過知識圖譜來建立供所有人共享且具有包容性的應用和資源。
本次目標：
- 學習如何為缺乏資源的語言建立知識圖譜。
- 認識工具和方法來協助保存原住民語言和知識。
- 建立知識圖譜的好處。
英文(en)
Level of Difficulty –簡易
Target Audience –Particpants interested on Wikibase, Wikidata, Minoritized languages, or low-resourced languages
Choose Venue for Publication –國際純線上(歐美時區友善)
Session Form –線上預錄
(EN)
I am currently pursuing a Ph.D. in Computer Science, which is strongly focused on knowledge graphs, their creation, curation, and deployment within the free knowledge ecosystem. I have work experience in project management, research, teaching, and writing and monitoring funding proposals. In addition, I have published
several articles and co-authored a book entitled Knowledge Graphs: Methodology, Tools and Selected Use Cases.
Also, I have participated in and won awards at a conference, hackathons, and datathons. Last but not least, I lead and monitor projects, programs, workshops, presentations, and talks related to knowledge management, minority communities, under-resourced and endangered languages, and media and information literacy.
(ZH)
我目前正在研讀計算機科學的博士學位，專注於在自由知識的生態系中建立、策畫、和設立知識圖譜。我曾擔任專案管理員、研究員、教師、以及資助專案的撰寫和監督。除此之外，我也發表了數篇文章，並共筆了《Knowledge Graphs: Methodology, Tools amd Selected Use Cases》一書。此外，我也曾在駭客松、數據松等活動中獲得獎項。最後，我也曾領銜數個有關知識管理、少數族群、缺乏資源和瀕危語言、以及媒體和資訊識讀的專案、工作坊、發表、和演說。