Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users
By Ondrej Dusek, Ondřej Plátek, Lukás Zilka, Filip Jurcícek. 2014
5 citations recorded by the source corpus.
When deploying a spoken dialogue system in a new domain, one faces a situation where little to no data is available to train domain-specific statistical models. We describe our experience with bootstrapping a dialogue system for public transit and weather information in real-word deployment under public use. We proceeded incrementally, starting from a minimal system put on a toll-free telephone number to collect speech data. We were able to incorporate statistical modules trained on collected data – in-domain speech recognition language models and spoken language understanding – while simultaneously extending the domain, making use of automatically generated semantic annotation. Our approach shows that a successful system can be built with minimal effort and no in-domain data at hand.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Ondrej Dusek
- Filip Jurvc'ivcek
- Filip Jurcícek
- Lukás Zilka
- Verena Rieser
- Jekaterina Novikova
- Yevgeniy Puzikov
- Mihir Kale
Citations in the corpus
- Neural Generation for Czech: Data and Baselines (2019, methodology): “Since there are few to none Czech speakers on crowdsourcing platforms (Pavlick et al., 2014; Duˇsek et al., 2014), we were not able to use them for data collection.”
- Incremental LSTM-based dialog state tracker (2015, background): “First, they can only track the dialog state turnby-turn (as opposed to a more complicated word-by-word approach), which limits their interaction with users: For example, in a typical dialog system [7, 8], the dialog system can”