Avancerad sökning

Visar resultat 1 - 5 av 75 avhandlingar som matchar ovanstående sökkriterier.

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. Multilingual text generation from structured formal representations

   Författare :Dana Dannélls; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Coherence; computational linguistics; coreference; corpus linguistics discourse structure; knowledge representation; language technology; lexical semantics; linked open data; multilingual natural language generation; natural language processing; ontology; semantic web.;

   Sammanfattning : This thesis aims to identify the optimal ways in which natural language generation techniques can be brought to bear upon the problem of processing a structured body of information in order to devise a coherent presentation of text content in multiple languages. We investigate how chains of referential expressions are realized in English, Swedish and Hebrew, and suggest several coreference strategies that can be used to generate coherent descriptions about paintings. LÄS MER

4. 3. Ask and distract : Data-driven methods for the automatic generation of multiple-choice reading comprehension questions from Swedish texts

   Författare :Dmytro Kalpakchi; Johan Boye; Joakim Nivre; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; multiple choice questions; question generation; distractor generation; reading comprehension; second-language learners; L2 learning; Natural Language Generation; flervalsfrågor; frågegenerering; distraktorsgenerering; läsförståelse; andraspråkslärande; L2-inlärning; Natural Language Generation; Speech and Music Communication; Tal- och musikkommunikation;

   Sammanfattning : Multiple choice questions (MCQs) are widely used for summative assessment in many different subjects. The tasks in this format are particularly appealing because they can be graded swiftly and automatically. LÄS MER

5. 4. Multilingual Abstractions: Abstract Syntax Trees and Universal Dependencies

   Författare :Kolachina Prasanth; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Grammatical Framework; Universal Dependencies; Natural Language Processing; multilinguality; abstract syntax trees; dependency trees; multilingual generation; multilingual parsers;

   Sammanfattning : This thesis studies the connections between parsing friendly representations and interlingua grammars developed for multilingual language generation. Parsing friendly representations refer to dependency tree representations that can be used for robust, accurate and scalable analysis of natural language text. LÄS MER

7. 5. Lexical and Grammar Resource Engineering for Runyankore & Rukiga: A Symbolic Approach

   Författare :David Bamutura; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; HUMANIORA; HUMANITIES; HUMANIORA; HUMANITIES; Computational Grammar; Runyankore; Grammar Resource; Grammatical Framework; Lexical Resource; Computational lexicon; Rukiga; Bantu Languages; Runyakitara; Resource Grammar Library; Language Resources; Grammar Engineering;

   Sammanfattning : Current research in computational linguistics and natural language processing (NLP) requires the existence of language resources. Whereas these resources are available for a few well-resourced languages, there are many languages that have been neglected. LÄS MER