Asia
IncorporatingBERTinto ParallelSequenceDecodingwithAdapters
While largescale pre-trained language models such asBERT[5]haveachieved greatsuccess onvariousnatural language understanding tasks,howtoefficiently and effectively incorporate them into sequence-to-sequence models and the corresponding text generation tasks remains a non-trivial problem.
Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding Jiangyan Ma1 Yifei Wang 2 Yisen Wang 3,4 1
Spectral embedding is a powerful graph embedding technique that has received a lot of attention recently due to its effectiveness on Graph Transformers.
Unsuper Lear
Delete, retrieve, generate: Asimpleapproachtosentiment transfer.
Contextual Bandits and Imitation Learning with Preference-Based Active Queries
We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward.
Contextual Bandits and Imitation Learning with Preference-Based Active Queries
We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward.
Multi-LexSum: Real-World Summariesof Civil Rights Lawsuitsat Multiple Granularities
EEOC sought injunctiverelief, as well as damages (including backpay) for the Black apprenticeshipapplicants. Don' t Give Methe Details, Just the Summary!
