Essays about: "semantisk likhet"

Showing result 1 - 5 of 9 essays containing the words semantisk likhet.

  1. 1. Evaluation of Sentence Representations in Semantic Text Similarity Tasks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Nils Balzar Ekenbäck; [2021]
    Keywords : sentence representations; semantic text similarity; sentence simi-larity; word embeddings; sentence embeddings; meningsrepresentation; semantisk textlikhet; meningslikhet; or-dinbäddningar; meningsinbäddningar;

    Abstract : This thesis explores the methods of representing sentence representations for semantic text similarity using word embeddings and benchmarks them against sentence based evaluation test sets. Two methods were used to evaluate the representations: STS Benchmark and STS Benchmark converted to a binary similarity task. READ MORE

  2. 2. Evaluating semantic similarity using sentence embeddings

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Jacob Malmberg; [2021]
    Keywords : ;

    Abstract : Semantic similarity search is the task of searching for documents or sentences which contain semantically similar content to a user-submitted search term. This task is often carried out, for instance when searching for information on the internet. READ MORE

  3. 3. Repairing Swedish Automatic Speech Recognition

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Karla Rehn; [2021]
    Keywords : Automatic speech recognition; Dialogue systems; Language models; ASR Repair; Automatisk taligenkänning; Dialogsystem; Språkmodeller; Reparation av taligenkänning;

    Abstract : The quality of automatic speech recognition has increased dramatically the last few years, but the performance for low and middle resource languages such as Swedish is still far from optimal. In this project a language model trained on large written corpora called KB-BERT is utilized to improve the quality of transcriptions for Swedish. READ MORE

  4. 4. Evaluating Unsupervised Methods for Out-of-Distribution Detection on Semantically Similar Image Data

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Magnus Pierrau; [2021]
    Keywords : Out-of-distribution detection; anomaly detection; semantic similarity; image data; comparative evaluation; synthetic image data; Out-of-distribution detektion; anomali detektion; semantisk likhet; bilddata; jämförande utvärdering; syntetisk bilddata;

    Abstract : Out-of-distribution detection considers methods used to detect data that deviates from the underlying data distribution used to train some machine learning model. This is an important topic, as artificial neural networks have previously been shown to be capable of producing arbitrarily confident predictions, even for anomalous samples that deviate from the training distribution. READ MORE

  5. 5. Identifying New Fault Types Using Transformer Embeddings

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Mikael Karlsson; [2021]
    Keywords : Transformer Models; Clustering; Embeddings; Deep Learning; Fault Identification; Transformatorbaserade modeller; Klustering; Djupinlärning; Felidentifiering;

    Abstract : Continuous integration/delivery and deployment consist of many automated tests, some of which may fail leading to faulty software. Similar faults may occur in different stages of the software production lifecycle and it is necessary to identify similar faults and cluster them into fault types in order to minimize troubleshooting time. READ MORE