Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Dekel, Avihu"'
Autor:
Dekel, Avihu, Fernandez, Raul
Tokenization algorithms that merge the units of a base vocabulary into larger, variable-rate units have become standard in natural language processing tasks. This idea, however, has been mostly overlooked when the vocabulary consists of phonemes or D
Externí odkaz:
http://arxiv.org/abs/2406.05547
Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is impractical for flue
Externí odkaz:
http://arxiv.org/abs/2309.11210
Publikováno v:
Proceedings: 36th Conference on Neural Information Processing Systems (NeurIPS), Dec 2022
Deep active learning aims to reduce the annotation cost for the training of deep models, which is notoriously data-hungry. Until recently, deep active learning methods were ineffectual in the low-budget regime, where only a small number of examples a
Externí odkaz:
http://arxiv.org/abs/2205.11320
Publikováno v:
39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022
Investigating active learning, we focus on the relation between the number of labeled examples (budget size), and suitable querying strategies. Our theoretical analysis shows a behavior reminiscent of phase transition: typical examples are best queri
Externí odkaz:
http://arxiv.org/abs/2202.02794