From post

Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions

, и . Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), стр. 8048--8073. Dublin, Ireland, Association for Computational Linguistics, (мая 2022)
DOI: 10.18653/v1/2022.acl-long.554

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

 

Другие публикации лиц с тем же именем

Conditional random fields: Probabilistic models for segmenting and labeling sequence data., , и . (2001)Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models., , , , и . CoRR, (2020)Unsupervised deduplication using cross-field dependencies., , и . KDD, стр. 310-317. ACM, (2008)Compact Representation of Uncertainty in Hierarchical Clustering., , , , , , , и . CoRR, (2020)Practical Markov Logic Containing First-Order Quantifiers with Application to Identity Uncertainty, и . Proceedings of the Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing, стр. 41--48. New York City, New York, Association for Computational Linguistics, (июня 2006)Training for Fast Sequential Prediction Using Dynamic Feature Selection., , и . CoRR, (2014)Efficiently Inducing Features of Conditional Random Fields. CoRR, (2012)Fast and Accurate Sequence Labeling with Iterated Dilated Convolutions., , , и . CoRR, (2017)Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension., , , , и . CoRR, (2018)Alternating Projections for Learning with Expectation Constraints, , и . CoRR, (2012)