2021 · Peer-reviewed journal article

Performance Trade-Off for Bert Based Multi-Domain Multilingual Chatbot Architectures

We tested whether separate chatbots could share one multilingual BERT model while keeping their own sets of possible answers.

Research question

Do thirteen chatbot tasks need thirteen models?

When a visitor asks a question, the chatbot picks a reply from answers the website has already written. This study tests whether several sites can share a single multilingual BERT classifier while each chatbot keeps its own answers.

The comparison covers 13 classification tasks and 333 categories across Turkish, English and German. It measures how sharing a model affects response selection accuracy, server memory and storage compared with training a separate model for each bot.

Source attribution
Davut Emre Taşar, Şükrü Ozan, Seçilay Kutal, Oğuzhan Ölmez, Semih Gülüm, Fatih Akca, Ceren Belhan
Publication status
Peer-reviewed journal article
Publication or platform
Journal of Artificial Intelligence and Data Science
Identifier
IZ:JA77UY82ER

Sources

Research areas · Language

Related work