Sökning: "language models"

Visar resultat 1 - 5 av 452 avhandlingar innehållade orden language models.

1. 1. Why the pond is not outside the frog? Grounding in contextual representations by neural language models

   Författare :Mehdi Ghanimifard; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computational linguistics; Language grounding; Spatial language; Distributional semantics; Computer vision; Language modelling; Vision and language; Neural language model; Grounded language model;

   Sammanfattning : In this thesis, to build a multi-modal system for language generation and understanding, we study grounded neural language models. Literature in psychology informs us that spatial cognition involves different aspects of knowledge that include visual perception and human interaction with the world. LÄS MER

3. 2. Improving Language Models Using Augmentation and Multi-Modality

   Författare :Tobias Norlund; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; natural language processing; contextual augmentation; multimodal language modeling; language models;

   Sammanfattning : Language models have become a core component in modern Natural Language Processing (NLP) as they constitute a powerful base that is easily adaptable to many language processing tasks. Part of the strength lies in their ability to embed associations representing general world knowledge. LÄS MER

4. 3. Natural Language Processing for Low-resourced Code-switched Colloquial Languages – The Case of Algerian Language

   Författare :Wafia Adouane; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Natural language processing; Deep neural networks; Low-resourced language; Colloquial language; Code-switch; Dialectal Arabic; User-generated data; Non-standardised orthography; Algerian language;

   Sammanfattning : In this thesis we explore to what extent deep neural networks (DNNs), trained end-to-end, can be used to perform natural language processing tasks for code-switched colloquial languages lacking both large automated data and processing tools, for instance tokenisers, morpho-syntactic and semantic parsers, etc. We opt for an end-to-end learning approach because this kind of data is hard to control due to its high orthographic and linguistic variability. LÄS MER

5. 4. Authentic Language : Övdalsk, metapragmatic exchange and the margins of Sweden’s linguistic market

   Författare :David Karlander; Kenneth Hyltenstam; Christopher Stroud; Tomas Riad; Judith T. Irvine; Stockholms universitet; []
   Nyckelord :HUMANIORA; HUMANITIES; HUMANIORA; HUMANITIES; authenticity; history of linguistic thought; indexicality; linguistic anthropology; linguistic minorities; metalanguage; metapragmatics; philosophical anthropology; Övdalsk; autenticitet; filosofisk antropologi; indexikalitet; lingvistisk antropologi; metaspråk; metapragmatik; språkliga minoriteter; språkvetenskapens idéhistoria; älvdalska; Bilingualism; tvåspråkighet;

   Sammanfattning : This compilation thesis engages with practices that in some way place stakes in the social existence of Övdalsk (also älvdalska, Elfdalian, Övdalian), a marginal form of Scandinavian used mainly in Sweden’s Älvdalen municipality. The practices at hand range from early 20th century descriptive dialectology and contemporary lay-linguistics to language advocacy and language political debate. LÄS MER

7. 5. Bayesian Models for Multilingual Word Alignment

   Författare :Robert Östling; Mats Wirén; Ola Knutsson; Jörg Tiedemann; Sharon Goldwater; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; word alignment; parallel text; Bayesian models; MCMC; linguistic typology; sign language; annotation transfer; transfer learning; Linguistics; lingvistik;

   Sammanfattning : In this thesis I explore Bayesian models for word alignment, how they can be improved through joint annotation transfer, and how they can be extended to parallel texts in more than two languages. In addition to these general methodological developments, I apply the algorithms to problems from sign language research and linguistic typology. LÄS MER