Avancerad sökning

Visar resultat 16 - 20 av 172 avhandlingar som matchar ovanstående sökkriterier.

  1. 16. Contracts and Computation — Formal modelling and analysis for normative natural language

    Författare :John J. Camilleri; Göteborgs universitet; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; normative texts; contract analysis; controlled natural language; model checking;

    Sammanfattning : Whether we are aware of it or not, our digital lives are governed by contracts of various kinds, such as privacy policies, software licenses, service agreements, and regulations. At their essence, normative documents like these dictate the permissions, obligations, and prohibitions of two or more parties entering into an agreement, including the penalties which must be paid when someone breaks the rules. LÄS MER

  3. 17. Who is laughing now? Laughter-infused dialogue systems

    Författare :Vladislav Maraev; Göteborgs universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; laughter; dialogue systems; humour; machine learning; reasoning; natural language processing; artificial agents;

    Sammanfattning : This thesis paves the way for including laughter in spoken dialogue systems in a domain-general and linguistically valid way using computational linguistics tools and methods. The thesis is concerned with three main areas. The first area concerns the placement of laughter in relation to speech and other behaviours. LÄS MER

  4. 18. Building Knowledge Graphs : Processing Infrastructure and Named Entity Linking

    Författare :Marcus Klang; Robotik och Semantiska System; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; natural language processing; machine learning; computational lingustics; named entity linking;

    Sammanfattning : Things such as organizations, persons, or locations are ubiquitous in all texts circulating on the internet, particularly in the news, forum posts, and social media. Today, there is more written material than any single person can read through during a typical lifespan. LÄS MER

  5. 19. Splitting rocks: Learning word sense representations from corpora and lexica

    Författare :Luis Nieto Piña; Göteborgs universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; language technology; natural language processing; distributional models; semantic representations; distributed representations; word senses; embeddings; word sense disambiguation; linguistic resources; corpus; lexicon; machine learning; neural networks;

    Sammanfattning : The representation of written language semantics is a central problem of language technology and a crucial component of many natural language processing applications, from part-of-speech tagging to text summarization. These representations of linguistic units, such as words or sentences, allow computer applications that work with language to process and manipulate the meaning of text. LÄS MER

  7. 20. A Picture is Worth a Thousand Words: Natural Language Processing in Context

    Författare :Lovisa Hagström; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NLP; Knowledge representation; Neural network; Vision-and-language models; Grounding; BERT;

    Sammanfattning : Modern NLP models learn language from lexical co-occurrences. While this method has allowed for significant breakthroughs, it has also exposed potential limitations of modern NLP methods. For example, NLP models are prone to hallucinate, represent a biased world view and may learn spurious correlations to solve the data instead of the task at hand. LÄS MER