Welcome!

Abstract: In this talk I present information about an attempt to model the lexical semantics of the Myanmar Language in the Myanmar Open Wordnet, a wordnet Open Multilingual Wordnet. It is an extension of the Princeton Wordnet of English, and one of the newest wordnets in the Open Multilingual Wordnet. I then talk about the Open Multilingual Wordnet, a large lexical network of words in many languages grouped into concepts and linked by typed semantic relations. The talk will cover how the resource has evolved over time (increases in both size and complexity) and introduce some of the latest extensions.

Abstract: Natural language processing (NLP) research is considered important because natural language is important for humankind. Today NLP research is data centric experientialism, often based on machine learning approaches. And thus, data resources are crucial and especially for under-resourced languages, it is hard to find relevant resources. Practically, NLP researchers who are working on under-resourced languages often have to consider developing resources such as POS-tagged corpora for word-category disambiguation, parallel corpora for machine translation and audio speech corpora for automatic speech recognition. In this talk, I will present the key aspects of my personal struggle for developing resources and tools for doing research in one of the under- resourced languages: Myanmar. I will also introduce some of my current NLP research work relating to OCR, spelling checker, Myanmar sign language, and Myanmar SignWriting.
 Dr. Ye will introduce his developing Myanmar Sign Language (MSL) corpus for Emergency Domain during poster section of the second day of the PACLING 2017 conference (17th Aug 2017) together with his students Ms. Swe Zin Moe (PhD student), Ms. Hlaing Myat Nwe (master student) and Ms. Hnin Wai Wai Hlaing (master student).