Page: 1 2 3 4 5 6 7 8 9 10... 629
101 |
Grammatical Gender Effects on Cross-linguistic Categorization ...
|
|
|
|
BASE
|
|
Show details
|
|
102 |
НОВЫЕ ПОДХОДЫ К ТИПОЛОГИИ ТЕРРИТОРИАЛЬНЫХ ВАРИАНТОВ ФРАНЦУЗСКОГО ЯЗЫКА ... : NEW APPROACHES TO THE TYPOLOGY OF TERRITORIAL VARIANTS OF THE FRENCH LANGUAGE ...
|
|
|
|
BASE
|
|
Show details
|
|
103 |
ПРИНИЦИПЫ КОГНИТИВНОГО МОДЕЛИРОВАНИЯ В ОБУЧЕНИИ ЯЗЫКУ ... : THE PRINCIPLES OF COGNITIVE MODELING IN LANGUAGE TEACHING ...
|
|
|
|
BASE
|
|
Show details
|
|
104 |
The expression of speaker and nonspeaker surprise in South Conchucos Quechua
|
|
|
|
BASE
|
|
Show details
|
|
107 |
Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning
|
|
|
|
Abstract:
Most of the world's languages suffer from the paucity of annotated data. This curbs the effectiveness of supervised learning, the most widespread approach to modelling language. Instead, an alternative paradigm could take inspiration from the propensity of children to acquire language from limited stimuli, in order to enable machines to learn any new language from a few examples. The abstract mechanisms underpinning this ability include 1) a set of in-born inductive biases and 2) the deep entrenchment of language in other perceptual and cognitive faculties, combined with the ability to transfer and recombine knowledge across these domains. The main contribution of my thesis is giving concrete form to both these intuitions. Firstly, I argue that endowing a neural network with the correct inductive biases is equivalent to constructing a prior distribution over its weights and its architecture (including connectivity patterns and non-linear activations). This prior is inferred by "reverse-engineering" a representative set of observed languages and harnessing typological features documented by linguists. Thus, I provide a unified framework for cross-lingual transfer and architecture search by recasting them as hierarchical Bayesian neural models. Secondly, the skills relevant to different language varieties and different tasks in natural language processing are deeply intertwined. Hence, the neural weights modelling the data for each of their combinations can be imagined as lying in a structured space. I introduce a Bayesian generative model of this space, which is factorised into latent variables representing each language and each task. By virtue of this modular design, predictions can generalise to unseen combinations by extrapolating from the data of observed combinations. The proposed models are empirically validated on a spectrum of language-related tasks (character-level language modelling, part-of-speech tagging, named entity recognition, and common-sense reasoning) and a typologically diverse sample of about a hundred languages. Compared to a series of competitive baselines, they achieve better performances in new languages in zero-shot and few-shot learning settings. In general, they hold promise to extend state-of-the-art language technology to under-resourced languages by means of sample efficiency and robustness to the cross-lingual variation. ; ERC (Consolidator Grant 648909) Lexical Google Research Faculty Award 2018
|
|
Keyword:
Bayesian Models; Deep Learning; Inductive Bias; Linguistic Typology; Modularity; Multilingual Natural Language Processing; Neural Networks; Sample Efficiency; Systematic Generalisation
|
|
URL: https://doi.org/10.17863/CAM.66424 https://www.repository.cam.ac.uk/handle/1810/319303
|
|
BASE
|
|
Hide details
|
|
108 |
Overcoming Word-Centrism: Towards a New Foundation for the Philosophy of Language ; Преодолевая словоцентризм: на пути к новым основаниям философии языка
|
|
|
|
BASE
|
|
Show details
|
|
110 |
Das Pronomen "sich" an der Schnittstelle von Reflexivität und Reziprozität
|
|
|
|
BASE
|
|
Show details
|
|
111 |
Syntaktische Interferenzerscheinungen in mündlichem Deutsch als Fremdsprache
|
|
|
|
BASE
|
|
Show details
|
|
112 |
Natural explanations for the history of word-final dental fricatives in English
|
|
|
|
BASE
|
|
Show details
|
|
113 |
Kontrastive Linguistik als Mikrotypologie: Die Rolle des Deutschen als L3
|
|
Livio Gaeta. - : Peter Lang, 2020. : country:DEU, 2020. : place:Berlin, 2020
|
|
BASE
|
|
Show details
|
|
114 |
Investigating differential case marking in Sümi, a language of Nagaland, using language documentation and experimental methods
|
|
|
|
BASE
|
|
Show details
|
|
115 |
Comparability and measurement in typological science: The bright future for linguistics
|
|
|
|
BASE
|
|
Show details
|
|
116 |
Semantic Categories of Artifacts and Animals Reflect Efficient Coding
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
117 |
Kalunga in the lusophone context: A phylogenetic study
|
|
|
|
In: Journal of Portuguese Linguistics, Vol 19, Iss 1 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
118 |
Kalunga in the lusophone context: A phylogenetic study
|
|
|
|
In: Journal of Portuguese Linguistics, Vol 19, Iss 1 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
119 |
Contextual Conditions and Constraints in Chinese Dangling Topics
|
|
|
|
In: Acta Linguistica Asiatica, Vol 10, Iss 2 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
120 |
Manner Verb Construction and Reduplication of Kedang Language: A Typological Study *
|
|
|
|
In: PAROLE: Journal of Linguistics and Education; Vol 10, No 2 (2020): Volume 10 Number 2 October 2020; 110-123 ; 23380683 ; 2087-345X (2020)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10... 629
|
|