Sparsity Emerges Naturally in Neural Language Models
University of Edinburgh（爱丁堡大学）
英文摘要：
Concerns about interpretability, computational resources, and principled inductive priors have motivated efforts to engineer sparse neural models for NLP tasks. If sparsity is important for NLP, might well-trained neural models naturally become roughly sparse? Using the Taxi-Euclidean norm to measure sparsity, we find that frequent input words are associated with concentrated or sparse activations, while frequent target words are associated with dispersed activations but concentrated gradients. We find that gradients associated with function words are more concentrated than the gradients of content words, even controlling for word frequency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
