Author of the publication

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

, and . Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), page 8048--8073. Dublin, Ireland, Association for Computational Linguistics, (May 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. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

Optimizing the decomposition for multiple foreground cosegmentation., and . Comput. Vis. Image Underst., (2015)Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks., , , , , , , , , and 1 other author(s). CoRR, (2019)Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings., , , , , , and . TextGraphs@NAACL-HLT, page 38-48. Association for Computational Linguistics, (2018)To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders., , and . WSDM, page 67-76. ACM, (2024)Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks., , , , , , , , , and 1 other author(s). J. Chem. Inf. Model., 60 (3): 1194-1201 (2020)Automatically Extracting Action Graphs from Materials Science Synthesis Procedures., , , , , , , , and . CoRR, (2017)Unsupervised Partial Sentence Matching for Cited Text Identification., , , and . SDP@COLING, page 95-104. Association for Computational Linguistics, (2022)Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling., , , and . ACL (1), page 821-854. Association for Computational Linguistics, (2023)Superpixel-based large displacement optical flow., and . ICIP, page 3835-3839. IEEE, (2013)Overcoming Practical Issues of Deep Active Learning and its Applications on Named Entity Recognition., , , , and . CoRR, (2019)