2024/11/01 by Sho Yokoi, Yokoi, Sho, Han Bao +5 · 2 citations
Agricultural and Biological Sciences · Biochemistry, Genetics and Molecular Biology · Chemistry · #Computation and Language (cs.CL) #Dye analysis and toxicity #FOS: Computer and information sciences #Garlic and Onion Studies #Machine Learning (cs.LG) #Machine Learning (stat.ML) #melanin and skin pigmentation
paper · pdf · doi:10.48550/arxiv.2411.00680
openalex publication_date 2024/11/01 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28
The word embedding space in neural models is skewed, and correcting this can improve task performance. We point out that most approaches for modeling, correcting, and measuring the symmetry of an embedding space implicitly assume that the word frequencies are uniform; in reality, word frequencies follow a highly non-uniform distribution, known as Zipf's law. Surprisingly, simply performing PCA whitening weighted by the empirical word frequency that follows Zipf's law significantly improves task performance, surpassing established baselines. From a theoretical perspective, both our approach and existing methods can be clearly categorized: word representations are distributed according to an exponential family with either uniform or Zipfian base measures. By adopting the latter approach, we can naturally emphasize informative low-frequency words in terms of their vector norm, which becomes evident from the information-geometric perspective, and in terms of the loss functions for imbalanced classification. Additionally, our theory corroborates that popular natural language processing methods, such as skip-gram negative sampling, WhiteningBERT, and headless language models, work well just because their word embeddings encode the empirical word frequency into the underlying probabilistic model.