Sökning: "mT5"

Hittade 3 uppsatser innehållade ordet mT5.

  1. 1. Automatic Semantic Role Labelling (SRL) in Swedish

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Lucy Yang Buhr; [2023-10-05]
    Nyckelord :Semantic role labelling; SRL; transfer learning; multi-task learning; multilingual transfer; T5; mT5;

    Sammanfattning : In this paper, using deep learning networks, the first end-to-end semantic role labelling model (SRL) has been developed for Swedish texts. This Swedish SRL model can, with a given Swedish sentence, perform trigger identification, frame classification and argument extraction tasks automatically in a series. LÄS MER

  3. 2. Smart Auto-completion in Live Chat Utilizing the Power of T5

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

    Författare :Zhanpeng Wang; [2021]
    Nyckelord :Natural Language Processing; Natural Language Generation; T5; Sequence-to- sequence; Auto-completion; Transformer-based Pre-trained Language Model; Naturlig språkbehandling; Generering av naturligt språk; T5; Sekvens-tillsekvens; Automatkomplettering; Transformatorbaserad förtränad språkmodell;

    Sammanfattning : Auto-completion is a task that requires an algorithm to give suggestions for completing sentences. Specifically, the history of live chat and the words already typed by the agents are provided to the algorithm for outputting the suggestions to finish the sentences. LÄS MER

  4. 3. Investigating the Effect of Complementary Information Stored in Multiple Languages on Question Answering Performance : A Study of the Multilingual-T5 for Extractive Question Answering

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

    Författare :Björn Aurell Hansson; [2021]
    Nyckelord :Machine learning; Transformers; multilingual-T5; question answering; NLP; Maskininlärning; transformatormodeller; frågeställning; naturlig språkbehandling.;

    Sammanfattning : Extractive question answering is a popular domain in the field of natural language processing, where machine learning models are tasked with answering questions given a context. Historically the field has been centered on monolingual models, but recently more and more multilingual models have been developed, such as Google’s MT5 [1]. LÄS MER