Semantic coordinates analysis reveals language changes in the AI field
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Freshman or Fresher? Quantifying the Geographic Variation of Internet Language
We present a new computational technique to detect and analyze statistically significant geographic variation in language. Our meta-analysis approach captures statistical properties of word usage across geographical regi…
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anchors and unembedding readout disagree on…
Measuring the Semantic Structure and Evolution of Conspiracy Theories
Research on conspiracy theories has largely focused on belief formation, exposure, and diffusion, while paying less attention to how their meanings change over time. This gap persists partly because conspiracy-related te…
Optical flow GNSS for navigation in the Indian subcontinent (NavIC)
This paper reveals about global navigation satellite system GNSS in the indian subcontinent known as the navigation in the indian subcontinent(NavIC) We have tried to model a new technique in GNSS known as the optical fl…
Optical Flow EstimationConceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dime…