Sökning: "Chatbot"

Visar resultat 1 - 5 av 106 uppsatser innehållade ordet Chatbot.

  1. 1. 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

  2. 2. Chatbot or voice assistant in a help desk application? : A study of users’ experiences and preferences

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Författare :Christina Metcalfe; [2021]
    Nyckelord :Conversation design; voice interaction; user experience; UX;

    Sammanfattning : Companies across a wide range of business areas are working hard to fulfill users wishes to speak to digital voice assistants. The trend of replacing chatbots in favour for voice assistants carries a risk of companies not considering which applications will actually benefit from getting a voice user interface (VUI) resulting in poor user experience. LÄS MER

  3. 3. Optimering av en chattbot för det svenska språket

    M1-uppsats, KTH/Hälsoinformatik och logistik; KTH/Hälsoinformatik och logistik

    Författare :Mohammed Mutaliev; Ibrahim Almimar; [2021]
    Nyckelord :Chatbots; machine learning; natural language processing; tokenization; feature extraction; classification; word embeddings; transformers; Chattbottar; maskininlärning; naturlig språkbearbetning; tokenisering; känneteckensextrahering; klassificering; ordinbäddningar; transformatorer;

    Sammanfattning : Chattbotutvecklare på Softronic använder i dagsläget Rasa-ramverket och dess standardkomponenter för bearbetning av användarinmatning. Det här är problematiskt då standardkomponenterna inte är optimerade för det svenska språket. LÄS MER

  4. 4. A retrieval-based chatbot ́s opinion on the trolley problem

    Kandidat-uppsats,

    Författare :Hampus Björklin; Tim Abrahamsson; Oscar Widenfalk; [2021]
    Nyckelord :chatbot; language model; trolley problem; BERT encoding; discord;

    Sammanfattning : The goal of this project was to create a chatbot capable of debating a user using limited resources including a discussion thread from the online debate forum Kialo. A retrieval based bot was designed and the discussion thread was converted into a database which the bot could interpret and choose an appropriate answer from. LÄS MER

  5. 5. Hi, I am the new digital co-worker : A qualitative study on employees within the public sector’s expectations and experiences of implementing AI chatbots

    Magister-uppsats, Högskolan Väst/Avd för informatik

    Författare :Josefine Kvarnåsen; [2021]
    Nyckelord :Chatbots; Public sector; Work impact; Communication;

    Sammanfattning : Chatbots are becoming increasingly common within both private and public sectors as they are implemented for organizations to provide service at any time. Within related research on the topic, the focus lies on the private sector and chatbot users, while the research on how chatbot implementation may affect the employees within the public sector is lacking. LÄS MER