DySem: Uncovering Dynamic Semantic Components via Multilingual Consensus for Calculating Semantic Textual Similarity (opens in new tab)

Calculating semantic textual similarity is a foundational task in natural language processing. Current large language models (LLMs) based methods typically rely on extracting last-layer hidden states with fixed dimensions to compute similarity for every text pairs. We argue that this paradigm is suffer from two limitations: (i) The last hidden layer encodes more general knowledge rather than just semantic knowledge, making it suboptimal for sema...