Semantic coordinates analysis reveals language changes in the AI field
arXiv:2011.00543
Abstract
Semantic shifts can reflect changes in beliefs across hundreds of years, but it is less clear whether trends in fast-changing communities across a short time can be detected. We propose semantic coordinates analysis, a method based on semantic shifts, that reveals changes in language within publications of a field (we use AI as example) across a short time span. We use GloVe-style probability ratios to quantify the shifting directions and extents from multiple viewpoints. We show that semantic coordinates analysis can detect shifts echoing changes of research interests (e.g., "deep" shifted further from "rigorous" to "neural"), and developments of research activities (e,g., "collaboration" contains less "competition" than "collaboration"), based on publications spanning as short as 10 years.
arXiv comment15 pages, 5 figures
References in corpus (9)
- Distributed Representations of Words and Phrases and their Compositionality
- Semantics derived automatically from language corpora contain human-like biases
- Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
- A Review of Challenges and Opportunities in Machine Learning for Health
- Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change
- Survey of Computational Approaches to Lexical Semantic Change
- The Scientific Method in the Science of Machine Learning
- HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning
- Avoiding a Tragedy of the Commons in the Peer Review Process