Alana v2: Entertaining and Informative Open-domain Social Dialogue using Ontologies and Entity Linking
By Amanda Cercas Curry, Ioannis V. Papaioannou, Alessandro Suglia, Shubham Agarwal, Igor Shalyminov, Xinnuo Xu, Ondrej Dusek, Arash Eshghi, Ioannis Konstas, Verena Rieser and 1 more. 2018
54 citations recorded by the source corpus.
Subfields: Natural Language Processing, LLM Agents & Tool Use
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
- Jason Aaron Edward Weston
- Emily Dinan
- Y-Lan Boureau
- Verena Rieser
- Mohit Bansal
- Dilek Z. Hakkani-Tür
- Dirk Hovy
- Gavin Abercrombie
Citations in the corpus
- Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “Cercas Curry et al. (2018) try different strategies to deal with abuse directed at their social chatbot, such as non-sequiturs, appeals to authority, and chastisement.”
- Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design (2022, background): “The possibility of adversarial interaction and, more generally, the unpredictability of a system used far outside the training distribution, make it particularly important to not exclusively rely on mitigations such as cleaning up training data to avoid exposing the system to offensive content, as i”
- Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations (2020, methodology): “While in the last Alexa Prize competition, none of the top three socialbots used neural generation (Chen et al., 2018; Pichi et al., 2018; Curry et al., 2018), we found current GPT-2 models (Radford et al.”
- Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize (2018, methodology): “In order to try to avoid generic and incoherent responses, Alana (Curry et al., 2018) built bot-specific classifiers using the dialogue context.”
- SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022, background): “Cercas Curry et al. (2018) try different strategies to deal with abuse directed at their social chat-bot, such as non-sequiturs, appeals to authority, and chastisement.”
- ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI (2021, background): “Following this report, several recent works have investigated possible abuse mitigation strategies (Cercas Curry and Rieser, 2018, 2019; Chin and Yi, 2019; Ma et al., 2019).”