magistrsko delo
Abstract
Klepetalniki in virtualni pomočniki postajajo vedno bolj prisotni v našem življenju. Uporabnikom omogočajo komunikacijo v govorjenem ali pisanem naravnem jeziku prek različnih kanalov za sporočanje. Slovenščine zaradi majhnega števila ljudi, ki jo uporabljamo za komuniciranje, globalno dostopni pametni pomočniki še ne podpirajo.
V našem delu smo razvili slovenskega virtualnega pomočnika za upravljanje pametnega doma, ki lahko z uporabo jezikovnega modela za razumevanje naravnega jezika določi namen in entitete v sporočilu uporabnika ter pri tem upošteva kontekst celotnega pogovora. Z uporabo pogovornega modela določi ime akcije, ki je zadolžena za generiranje odgovora. V akcijah smo implementirali različna znanja, s katerimi je lahko uporabnik pridobil številne informacije in izvajal različna opravila.
Razvili in evalvirali smo več različnih modelov za klasifikacijo namena in prepoznavo entitet. Najvišjo uspešnost pri klasifikaciji namena smo dosegli z uporabo vektorskih vložitev jezikovnega modela SloBERTa (ocena F1 = 0,900). Pri ekstrakciji entitet smo najvišjo uspešnost dosegli z uporabo vektorskih vložitev modela fastText (ocena F1 = 0,924).
Keywords
klepetalnik;virtualni pomočnik;obdelava naravnega jezika;naravno razumevanje jezika;transformer;Rasa;multimedija;računalništvo;magisteriji;
Data
Language: |
Slovenian |
Year of publishing: |
2021 |
Typology: |
2.09 - Master's Thesis |
Organization: |
UL FRI - Faculty of Computer and Information Science |
Publisher: |
[V. Čermelj] |
UDC: |
004.032.6:004.946(043.2) |
COBISS: |
64763907
|
Views: |
450 |
Downloads: |
157 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Slovenian virtual assistant for smart home management |
Secondary abstract: |
Chatbots and virtual assistants are becoming more and more present in our lives. They allow users to communicate in spoken or written natural language, through various communication channels. Slovenian language is poorly supported by globally used smart assistants, due to the small number of people that use it for communication.
We have developed a Slovenian virtual assistant for smart home management. The assistant understands natural language and uses a language model to classify the purpose and entities in the user's message by taking the context of the entire conversation into account. It uses a conversational model to determine the name of the action responsible for generating the response. We used actions to implement various skills. They enable users to obtain various information and perform different tasks.
In our thesis, we have developed and evaluated several different models for intent classification and entity extraction. The highest performance in the intent classification was achieved by using word embeddings from the SloBERTa language model (F1 score = 0,900). In the extraction of entities, the highest performance was achieved by using word embeddings from the fastText model (F1 score = 0.924). |
Secondary keywords: |
chatbot;virtual assistant;natural language processing;natural language understanding;transformer;Rasa;multimedia;computer science;master's degree; |
Type (COBISS): |
Master's thesis/paper |
Study programme: |
1001017 |
Embargo end date (OpenAIRE): |
1970-01-01 |
Thesis comment: |
Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Pages: |
82 str. |
ID: |
12895815 |