Proceedings of the 10th SIGHAN workshop on Chinese language processing

The SIGHAN workshop returned and co-located with the 62nd Annual Meeting of the Association for Computational Linguistics (ACL-2024) in Bangkok, Thailand on August 11–16, 2024.  

In an increasingly interconnected world, the importance of Chinese language processing cannot be overstated. As one of the most widely spoken languages, Chinese presents unique challenges and opportunities in the current research of artificial intelligence. Effective processing of the Chinese language opens doors to vast markets and cultural exchanges, fostering global collaboration and understanding. It serves as a critical tool in bridging linguistic divides and unlocking the rich textual heritage and contemporary content in Chinese. The focus of this workshop delves into the challenges in processing of the Chinese language, especially within the technology explosion of large language model, to explore how the Chinese specific tasks can be optimised to effectively understand as well as generating Chinese text, addressing both technical hurdles and linguistic nuances.

The topics include but not limit to:

• Corpus Development for Chinese Computing: A cornerstone of language processing is a robust corpus. This workshop aims to explore strategies for building comprehensive and diverse Chinese language corpora that can serve as the foundation for effective computational analysis and language model training.

• Large Language Models for Chinese Computing: Another key aim is to delve into the development and refinement of large language models specifically tailored for Chinese language processing. This includes addressing the challenges of dialectal variations, idiomatic expressions, and the integration of cultural context.

• Multilingual Methods for Chinese Computing: Recognizing the global context in which Chinese language processing operates, the workshop will focus on multilingual approaches that facilitate seamless interaction between Chinese and other languages, enhancing cross-lingual communication and data exchange.

• Knowledge-Driven Methods for Chinese Computing: The workshop will explore knowledge-driven approaches in Chinese computing. This involves leveraging structured knowledge sources and semantic understanding to improve the accuracy and context-awareness of Chinese language processing systems.

Join us in navigating the complexities and uncovering the potential of Chinese language processing, an endeavour that promises to shape the future of global communication and AI development.