Sökning: "behandling av naturligt språk"

Visar resultat 1 - 5 av 13 uppsatser innehållade orden behandling av naturligt språk.

1. 1. A Prompting Framework for Natural Language Processing in the Medical Field : Assessing the Potential of Large Language Models for Swedish Healthcare

   Master-uppsats, KTH/Medicinteknik och hälsosystem

   Författare :Anim Mondal; [2023]
   Nyckelord :Healthcare; NLP; GPT; framework; medical; AI; Hälsovård; NLP; GPT; ramverk; medicin; AI;

   Sammanfattning : The increasing digitisation of healthcare through the use of technology and artificial intelligence has affected the medical field in a multitude of ways. Generative Pre-trained Transformers (GPTs) is a collection of language models that have been trained on an extensive data set to generate human-like text and have been shown to achieve a strong understanding of natural language. LÄS MER

3. 2. Information Extraction from Invoices using Graph Neural Networks

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

   Författare :Tuoyuan Tan; [2023]
   Nyckelord :Natural Language Processing; Information Extraction; Graph Neural Networks; Invoice; Behandling av naturligt språk; informationsutvinning; grafiska neurala nätverk; faktura;

   Sammanfattning : Information Extraction is a sub-field of Natural Language Processing that aims to extract structured data from unstructured sources. With the progress in digitization, extracting key information like account number, gross amount, etc. from business invoices becomes an interesting problem in both industry and academy. LÄS MER

4. 3. An Arrow Metalanguage for Partially Invertible Computation

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

   Författare :Anders Ågren Thuné; [2023]
   Nyckelord :Reversible computation; Domain-specific languages; Arrows; Partial invertibility; Reversibel beräkning; Domänspecifika språk; Arrows; Partiell inverterbarhet;

   Sammanfattning : Programming languages traditionally describe computations going one way: a program might compute a hash value from a string, or an encrypted message from a plaintext. However, sometimes it is also of interest to go the other way around: for encryption, we not only want to encrypt messages but also to decrypt them, and to be sure that the decryption correctly reproduces the original message. LÄS MER

5. 4. Transformer-Based Multi-scale Technical Reports Analyser for Science Projects Cost Prediction

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

   Författare :Thomas Bouquet; [2023]
   Nyckelord :Natural Language Processing; Transformers; Deep Learning; Cost Prediction; Traitement Automatique du Langage; Transformers; Apprentissage Profond; Prédiction de coûts; Behandling av naturligt språk; Transformers; Djupinlärning; Kostnadsförutsägelser;

   Sammanfattning : Intrinsic value prediction is a Natural Language Processing (NLP) problem consisting in determining a numerical value contained implicitly and non-trivially in a text. In this project, we introduce the SWORDSMAN model (Sentence and Word-level Oracle for Research Documents by Semantic Multi-scale ANalysis), a deep neural network architecture based on transformers whose goal is to predict the cost of research projects from the analysis of their abstract. LÄS MER

7. 5. Root Cause Analysis and Classification for Firewall Log Events Using NLP Methods

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

   Författare :Tongxin Wang; [2022]
   Nyckelord :Log Analysis; BERT; Natural Language Processing; Log Classification; Transformers; Log Analysis; BERT; Naturligt språk-behandling; Log-Klassificering; Transformers;

   Sammanfattning : Network log records are robust evidence for enterprises to make error diagnoses. The current method of Ericsson’s Networks team for troubleshooting is mainly by manual observation. However, as the system is getting vast and complex, the log messages show a growth trend. LÄS MER