Smoothening of Software documentation : comparing a self-made sequence to sequence model to a pre-trained model GPT-2
This thesis was done in collaboration with Ericsson AB with the goal of researching the possibility of creating a machine learning model that can transfer the style of a text into another arbitrary style depending on the data used. This had the purpose of making their technical documentation appear...
Main Authors: | Tao, Joakim, Thimrén, David |
---|---|
Format: | Others |
Language: | English |
Published: |
Linköpings universitet, Institutionen för datavetenskap
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-178186 |
Similar Items
-
Controlled Languages in Software User Documentation
by: Steensland, Henrik, et al.
Published: (2005) -
Using Attention-based Sequence-to-Sequence Neural Networks for Transcription of Historical Cipher Documents
by: Renfei, Han
Published: (2020) -
Clustering in Swedish : The Impact of some Properties of the Swedish Language on Document Clustering and an Evaluation Method
by: Rosell, Magnus
Published: (2005) -
Fördomsfulla associationer i en svenskvektorbaserad semantisk modell
by: Jonasson, Michael
Published: (2019) -
Creating Knowledge Graphs using Distributional Semantic Models
by: Sandelius, Hugo
Published: (2016)