Computational Models for Semantic Change and their Applications in Multidisciplinary Research

This course introduces students to lexical semantic change research. It will provide an overview of NLP models for word meaning representations from past to state-of-the-art. It will survey existing resources of diachronic data in the form of historical corpora, reliable datasets, and evaluation. It will cover the application of semantic change methods for varied fields like historical linguistics, sociology, or cultural studies.

Focusing on tools for detecting and interpreting semantic change, the course emphasizes their relevance to any research disciplines that uses text as its main medium of study. By analyzing diachronic corpora with state-of-the-art methods, students gain insights into societal attitudes towards various topics over time, from technology acceptance to racial bias in legal texts. The course blends theoretical foundations with hands-on practice, enabling participants to navigate computational tools in NLP effectively. Delving into challenges and adjustments for cross-disciplinary deployment, the course train students to select appropriate methods for their research scenarios. Ultimately, participants will emerge with a nuanced understanding of semantic change and the practical skills to apply computational tools judiciously in diverse research contexts.

References:

• Nina Tahmasebi, Adam Jatowt, Lars Borin. Survey of Computational Approaches to Lexical Semantic Change Detection. Nina Tahmasebi, Lars Borin, Adam Jatowt, Yang Xu, Simon Hengchen (eds). Computational Approaches to Semantic Change. Berlin: Language Science Press.
• Stefano Montanelli, Francesco Periti. A Survey on Contextualised Semantic Shift Detection. arXiv preprint arXiv:2304.01666.
• Dubossarsky, H., Weinshall, D., & Grossman, E. (2017, September). Outta control: Laws of semantic change and inherent biases in word representation models. In Proceedings of the 2017 conference on empirical methods in natural language processing (pp. 1136-1145).
• Geeraerts, D. (2020). Semantic Change. In The Wiley Blackwell Companion to Semantics (eds D. Gutzmann, L. Matthewson, C. Meier, H. Rullmann and T. Zimmermann).
• Simon Hengchen, Nina Tahmasebi, Dominik Schlechtweg, Haim Dubossarsky. Challenges for Computational Lexical Semantic Change. Nina Tahmasebi, Lars Borin, Adam Jatowt, Yang Xu, Simon Hengchen (eds). Computational Approaches to Semantic Change. Berlin: Language Science Press.
• Pierluigi Cassotti, Lucia Siciliani, Marco DeGemmis, Giovanni Semeraro, Pierpaolo Basile, XL-LEXEME: WiC Pretrained Model for Cross-Lingual LEXical sEMantic changE. (2023) In Proc. of ACL2023
• Francesco Periti and Nina Tahmasebi. A Systematic Comparison of Contextualized Word Embeddings for Lexical Semantic Change. (2024) arXiv:2402.12011.
• Dominik Schlechtweg, Nina Tahmasebi, Simon Hengchen, Haim Dubossarsky, and Barbara McGillivray. DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languages. . In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7079–7091, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.