Unifying a Large Language Model and Company Specific Terminology for Enhanced Translation in a Company’s Multilingual Landscape
Information
Författare: Alexander Andersson, Vilma CaracoliasBeräknat färdigt: 2024-06
Handledare: Mathias Ljungberg
Handledares företag/institution: Ahlsell
Ämnesgranskare: Ekta Vats
Övrigt: -
Presentationer
Presentation av Alexander AnderssonPresentationstid: 2024-05-23 11:15
Presentation av Vilma Caracolias
Presentationstid: 2024-05-23 12:15
Opponenter: Arvid Zetterberg, Simon Pettersson Palestro
Abstract
This thesis investigates the possibility of integrating a large language model with industry-specific terminology to enhance translation accuracy in Ahlsell’s daily operations. Additionally, the thesis seeks to identify effective strategies for implementing a translation tool within the organization’s operations by using the change management model ADKAR. Dictionaries and synonyms of industry-specific words were used to provide desired translations to an existing translation model. Translations were conducted on product descriptions and evaluated with BLEU-scores. A test group was formed to evaluate translations and identify words to be added to the dictionaries. Furthermore, meetings and demos were held with the goal to spread information and retrieve feedback. Impact goals were also set at the beginning of the project to state the desired outcomes of the implementation. The research has yielded a functional and efficient translation model employing GPT-4, incorporating a dictionary and synonyms tailored for translation between English and Nordic languages within Ahlsell’s operations. This study initiated the establishment of a company-specific dictionary, aimed at further refining translation capabilities. The study also found that considerations such as establishing clear responsibility guidelines and effective information dissemination strategies should be prioritized in the future for a successful implementation of the translation tool.