This workshop aims to invite researchers from different backgrounds to share their latest work in NLP and speech approaches to South East Asian languages. Topics of relevance to the workshop include the following:

  • Development of resources (dataset/testbed/pre-trained language models/etc) to support research on South East Asian languages
  • Development of publicly available and replicable benchmarks for comparing NLP techniques on South East Asian languages
  • Development of NLP techniques specifically designed for South East Asian languages
  • Development of NLP techniques applicable for South East Asian languages: e.g., NLP techniques for low-resource languages, NLP techniques for morphologically complex languages, NLP techniques for code-switching, NLP techniques for informal forms of languages, etc.
  • Application of existing NLP techniques to South East Asian languages for which published results do not exist, and/or accompanying analysis
  • Analysis of linguistic and cultural diversity in South East Asia
  • Challenges for NLP in South East Asian languages
  • Ethical issues and considerations of NLP for South East Asian languages
  • Utilization and/or evaluation of large language models in the context of South East Asian languages and/or countries
  • NLP Applications in the context of South East Asian languages and/or countries

We accept both archival and non-archival submissions. All submissions will be processed through Softconf by following this link. Submission is double-blind and should follow the ACL template. We accept both short (4 pages) and long (8 pages) submissions.