Viola: A Topic Agnostic Generate-and-Rank Dialogue System

by   Hyundong Cho, et al.

We present Viola, an open-domain dialogue system for spoken conversation that uses a topic-agnostic dialogue manager based on a simple generate-and-rank approach. Leveraging recent advances of generative dialogue systems powered by large language models, Viola fetches a batch of response candidates from various neural dialogue models trained with different datasets and knowledge-grounding inputs. Additional responses originating from template-based generators are also considered, depending on the user's input and detected entities. The hand-crafted generators build on a dynamic knowledge graph injected with rich content that is crawled from the web and automatically processed on a daily basis. Viola's response ranker is a fine-tuned polyencoder that chooses the best response given the dialogue history. While dedicated annotations for the polyencoder alone can indirectly steer it away from choosing problematic responses, we add rule-based safety nets to detect neural degeneration and a dedicated classifier to filter out offensive content. We analyze conversations that Viola took part in for the Alexa Prize Socialbot Grand Challenge 4 and discuss the strengths and weaknesses of our approach. Lastly, we suggest future work with a focus on curating conversation data specifcially for socialbots that will contribute towards a more robust data-driven socialbot.


page 6

page 14

page 16


A Transformer-based Response Evaluator for Open-Domain Spoken Conversation

Many open-domain dialogue systems rely on multiple response generators, ...

Proto: A Neural Cocktail for Generating Appealing Conversations

In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: P...

Athena: Constructing Dialogues Dynamically with Discourse Constraints

This report describes Athena, a dialogue system for spoken conversation ...

Production Ready Chatbots: Generate if not Retrieve

In this paper, we present a hybrid model that combines a neural conversa...

Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts

Dialogue models trained on human conversations inadvertently learn to ge...

Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding

Dialogue systems powered by large pre-trained language models (LM) exhib...

Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems

Neural approaches to Natural Language Generation (NLG) have been promisi...

Please sign up or login with your details

Forgot password? Click here to reset