| Title |
Dialogue system augmented with commonsense knowledge / |
| Authors |
Lasy, Ilya ; Marcinkevičius, Virginijus |
| DOI |
10.15388/LMITT.2022.7 |
| eISBN |
9786090707425 |
| Full Text |
|
| Is Part of |
Vilnius University Open Series: Konferencijos „Lietuvos magistrantų informatikos ir IT tyrimai“ darbai", 2022 m. gegužės 16 d... Vilnius : Vilniaus universiteto leidykla, 2022. p. 68-76.. eISSN 2669-0535. eISBN 9786090707425 |
| Keywords [eng] |
natural language generation ; dialogue system ; chat-bot ; knowledge graph ; deep learning |
| 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-theart 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 proposed which is then used to incorporate knowledge into existing dialogue datasets. Current state-of-theart model BlenderBot is finetuned on new datasets which shows improvement in novelty of utterances generated by the model. |
| Published |
Vilnius : Vilniaus universiteto leidykla, 2022 |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2022 |
| CC license |
|
