| Title |
Development of dialogue system augmented with commonsense knowledge / |
| Translation of Title |
Pokalbių sistemos naudojančios bendras žinias įgyvendinimas. |
| Authors |
Lasy, Ilya |
| Full Text |
|
| Pages |
46 |
| Keywords [eng] |
Natural Language Generation, Dialogue System, Knowledge Graph, Deep Learning, Transformers |
| Abstract [eng] |
Building an open-domain dialog system is a challenging task in current research. In order to successfully maintain a conversation with human, a dialog system must develop many qualities: being engaging, empathetic, show a unique personality and having general knowledge about the world. Prior research has shown that it is possible to develop such chat-bot system that combines these features, but this work explores this problem further. Most state-of-the-art dialogue systems are guided by unstructured knowledge such as Wikipedia articles, but there is a lack of research on how structured knowledge bases can be used for open-domain dialogue generation. This work proposes usage of structured knowledge base ConceptNet for knowledge-grounded dialogue generation. Novel knowledge extraction algorithm is developed which is then used to incorporate knowledge into existing dialogue datasets. Current state-of-the-art model BlenderBot is finetuned on newly created datasets and it is shown that knowledge augmentation of the dataset improved BlenderBot in terms of various automated metrics and according to human evaluation. |
| Dissertation Institution |
Vilniaus universitetas. |
| Type |
Master thesis |
| Language |
English |
| Publication date |
2022 |
