Zobrazeno 1 - 10
of 55
pro vyhledávání: '"Matusevych, Yevgen"'
Choosy Babies Need One Coach: Inducing Mode-Seeking Behavior in BabyLlama with Reverse KL Divergence
This study presents our submission to the Strict-Small Track of the 2nd BabyLM Challenge. We use a teacher-student distillation setup with the BabyLLaMa model (Timiryasov and Tastet, 2023) as a backbone. To make the student's learning process more fo
Externí odkaz:
http://arxiv.org/abs/2410.22081
When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: a novel word is mapped to a novel object rather than a familiar one. This bias has been studied computationally, but only in models that use discrete wor
Externí odkaz:
http://arxiv.org/abs/2403.13922
Autor:
Matusevych, Yevgen1 (AUTHOR) yevgen.matusevych@rug.nl
Publikováno v:
Computational Linguistics. Sep2024, Vol. 50 Issue 3, p1049-1052. 4p.
Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoencoder-based recurrent models. An
Externí odkaz:
http://arxiv.org/abs/2103.10731
Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these difficulties can ari
Externí odkaz:
http://arxiv.org/abs/2101.11332
Publikováno v:
2020. In S. Denison, M. Mack, Y. Xu, and B. Armstrong (Eds.), Proceedings of the 42nd Annual Conference of the Cognitive Science Society (pp. 571-577). Austin, TX: Cognitive Science Society
In the first year of life, infants' speech perception becomes attuned to the sounds of their native language. Many accounts of this early phonetic learning exist, but computational models predicting the attunement patterns observed in infants from th
Externí odkaz:
http://arxiv.org/abs/2008.02888
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In zero-reso
Externí odkaz:
http://arxiv.org/abs/2006.02295
Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---fixed-size vector representations of words which encode their acoustic features. Despite the widespread use of AWEs in speech processing research, they have only be
Externí odkaz:
http://arxiv.org/abs/2004.01647
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing and discover
Externí odkaz:
http://arxiv.org/abs/2002.02109
The cognitive mechanisms needed to account for the English past tense have long been a subject of debate in linguistics and cognitive science. Neural network models were proposed early on, but were shown to have clear flaws. Recently, however, Kirov
Externí odkaz:
http://arxiv.org/abs/1906.01280