Search for dissertations about: "natural language"

Showing result 1 - 5 of 772 swedish dissertations containing the words natural language.

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

   Author : Wafia Adouane; Göteborgs universitet; []
   Keywords : 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;

   Abstract : 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. READ MORE

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

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

   Abstract : 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. READ MORE

5. 3. Representation learning for natural language

   Author : Olof Mogren; RISE; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; artificial neural networks; artificial intelligence; natural language processing; deep learning; machine learning; summarization; representation learning;

   Abstract : Artificial neural networks have obtained astonishing results in a diverse number of tasks. One of the reasons for the success is their ability to learn the whole task at once (endto-end learning), including the representations for data. READ MORE

6. 4. Developing and Evaluating Language Tools for Writers and Learners of Swedish

   Author : Ola Knutsson; Kerstin Severinson Eklundh; Viggo Kann; Teresa Cerratto Pargman; Lars Ahrenberg; KTH; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; interactive learning systems; error; feedback; human-computer interaction; grammar checking; grammaticality judgments; parsing; second language learning; Swedish; evaluation; user studies; language technology; computer assisted language learning; writing; language tools; interaktiva lärsystem; fel; återkoppling; grammatikkontroll; språkverktyg; människa-datorinteraktion; skrivande; andraspråksinlärning; grammatikalitetsbedömning; parsning; Language technology; Språkteknologi;

   Abstract : Skrivande och skrivet språk är idag en viktig del av många människors liv, i datorns ordbehandlare, i e-postprogram och i chattkanaler på Internet. Skrivet språk har blivit mer eller mindre en förutsättning för människors dagliga kommunikation. Denna utveckling av samhället leder till ökade behov av att på olika sätt hantera text. READ MORE

7. 5. Exploring natural language processing for single-word and multi-word lexical complexity from a second language learner perspective

   Author : David Alfter; Göteborgs universitet; []
   Keywords : HUMANIORA; HUMANITIES; NATURVETENSKAP; NATURAL SCIENCES; natural language processing; lexical complexity; CEFR; second language learning; machine learning; crowdsourcing;

   Abstract : In this thesis, we investigate how natural language processing (NLP) tools and techniques can be applied to vocabulary aimed at second language learners of Swedish in order to classify vocabulary items into different proficiency levels suitable for learners of different levels. In the first part, we use feature-engineering to represent words as vectors and feed these vectors into machine learning algorithms in order to (1) learn CEFR labels from the input data and (2) predict the CEFR level of unseen words. READ MORE