IsoScore: Measuring the Uniformity of Embedding Space Utilization
暂无分享,去创建一个
[1] Maksim Podkorytov,et al. Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications , 2021, NAACL.
[2] Jie Zheng,et al. Learning to Remove: Towards Isotropic Pre-trained BERT Embedding , 2021, ICANN.
[3] Bill Yuchen Lin,et al. IsoBN: Fine-Tuning BERT with Isotropic Batch Normalization , 2020, AAAI.
[4] Kenneth Ward Church,et al. Isotropy in the Contextual Embedding Space: Clusters and Manifolds , 2021, ICLR.
[5] Kees van Deemter,et al. What do you mean, BERT? Assessing BERT as a Distributional Semantics Model , 2019, ArXiv.
[6] Thomas Wolf,et al. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.
[7] Kawin Ethayarajh,et al. How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings , 2019, EMNLP.
[8] Shaowu Zhang,et al. Refining Word Representations by Manifold Learning , 2019, IJCAI.
[9] Jordan Rodu,et al. Getting in Shape: Word Embedding SubSpaces , 2019, IJCAI.
[10] Di He,et al. Representation Degeneration Problem in Training Natural Language Generation Models , 2019, ICLR.
[11] Martin Wattenberg,et al. Visualizing and Measuring the Geometry of BERT , 2019, NeurIPS.
[12] Christopher D. Manning,et al. A Structural Probe for Finding Syntax in Word Representations , 2019, NAACL.
[13] Dilin Wang,et al. Improving Neural Language Modeling via Adversarial Training , 2019, ICML.
[14] Ming-Wei Chang,et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.
[15] Ilya Sutskever,et al. Language Models are Unsupervised Multitask Learners , 2019 .
[16] Di He,et al. FRAGE: Frequency-Agnostic Word Representation , 2018, NeurIPS.
[17] Pramod Viswanath,et al. All-but-the-Top: Simple and Effective Postprocessing for Word Representations , 2017, ICLR.
[18] Alec Radford,et al. Improving Language Understanding by Generative Pre-Training , 2018 .
[19] Edward Curry,et al. Word Re-Embedding via Manifold Dimensionality Retention , 2017, EMNLP.
[20] Richard Socher,et al. Pointer Sentinel Mixture Models , 2016, ICLR.
[21] P. Campadelli,et al. Intrinsic Dimension Estimation: Relevant Techniques and a Benchmark Framework , 2015 .
[22] Sanjeev Arora,et al. Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings , 2015, ArXiv.
[23] Peter J. Bickel,et al. Maximum Likelihood Estimation of Intrinsic Dimension , 2004, NIPS.