Sökning: "natural language processing"

Visar resultat 1 - 5 av 344 uppsatser innehållade orden natural language processing.

  1. 1. Natural Language Processing Model for Maltese Syntax

    Magister-uppsats, Göteborgs universitet/Institutionen för filosofi, lingvistik och vetenskapsteori

    Författare :Greta Attard; [2021-10-08]
    Nyckelord :natural language processing; syntax; spaCy; universal dependency; dependency parser; part-of-speech tagger; maltese nlp pipeline;

    Sammanfattning : The objective of this thesis is to create a Natural Language Processing Model for theMaltese Language. The ultimate goal is that the model would be able to recognise syntactical features, that is the linguistic features and the relationship of a sequence of words, in Maltese. LÄS MER

  2. 2. Understand me, do you? : An experiment exploring the natural language understanding of two open source chatbots

    M1-uppsats, Blekinge Tekniska Högskola/Institutionen för programvaruteknik; Blekinge Tekniska Högskola/Institutionen för programvaruteknik

    Författare :Linnéa Olofsson; Heidi Patja; [2021]
    Nyckelord :chatbot; natural language processing; natural language understanding; intent classification;

    Sammanfattning : What do you think of when you hear the word chatbot? A helpful assistant when booking flight tickets? Maybe a frustrating encounter with a company’s customer support, or smart technologies that will eventually take over your job? The field of chatbots is under constant development and bots are more and more taking a place in our everyday life, but how well do they really understand us humans?  The objective of this thesis is to investigate how capable two open source chatbots are in understanding human language when given input containing spelling errors, synonyms or faulty syntax. The study will further investigate if the bots get better at identifying what the user’s intention is when supplied with more training data to base their analysis on. LÄS MER

  3. 3. Key-Challenges of Public Procurement of AI in the Swedish Public Sector : Case study at IBM with a focus on NLP Technologies

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Mikaela Trygg; [2021]
    Nyckelord :AI; NLP; Public Procurement; Public Sector; Digital Competence; Digital Skills Gap;

    Sammanfattning : The economic potential in introducing Artificial Intelligence (AI) into the Swedish Public administration is substantial and it is calculated to be approximately 140B SEK per year[5]. However, without a comprehensive AI strategy and lack of sufficient digital competence, an AI implementation becomes a struggle [9]. LÄS MER

  4. 4. Smart Compose for Live Chat Agent

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Tonghua Zhang; [2021]
    Nyckelord :Deep learning; Natural language processing; Transformer; Text generation; Auto- completion; Djupinlärning; Naturlig språkbehandling; Transformator; Textgenerering; Automatisk komplettering;

    Sammanfattning : In the digital business environment, customer service communication has grown up to become a labor- intensive task. In consideration of high labor costs, automatic customer service could be such a good alternative for many companies. However, communication with customers can not be easily automated. LÄS MER

  5. 5. Natural Language Processing Model for Log Analysis to Retrieve Solutions For Troubleshooting Processes

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Núria Marzo i Grimalt; [2021]
    Nyckelord :Trouble Report; Recommender System; BERT; Information Retrieval; Natural Language Processing; Multi-Stage Ranking; Felrapporter; Rekommendatorsystem; BERT; Informationsinhämtning; Naturlig Språkbehandling; Dubbelriktade Ranking;

    Sammanfattning : In the telecommunications industry, one of the most time-consuming tasks is troubleshooting and the resolution of Trouble Report (TR) tickets. This task involves the understanding of textual data which can be challenging due to its domain- and company-specific features. LÄS MER