Open-Domain Dialog

32 papers with code • 1 benchmarks • 11 datasets

This task has no description! Would you like to contribute one?

Latest papers with no code

Social Commonsense-Guided Search Query Generation for Open-Domain Knowledge-Powered Conversations

no code yet • 22 Oct 2023

Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations.

Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog

no code yet • 20 Dec 2022

To better mimic human-level conversations that usually fuse various dialog modes, it is essential to build a system that can effectively handle both TOD and ODD and access different knowledge sources.

Interactive Evaluation of Dialog Track at DSTC9

no code yet • LREC 2022

Our track challenges participants to develop strong response generation models and explore strategies that extend them to back-and-forth interactions with real users.

Towards Learning Through Open-Domain Dialog

no code yet • 7 Feb 2022

The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them.

An Empirical Study of Topic Transition in Dialogue

no code yet • COLING (CODI, CRAC) 2022

Transitioning between topics is a natural component of human-human dialog.

User Response and Sentiment Prediction for Automatic Dialogue Evaluation

no code yet • 16 Nov 2021

Automatic evaluation is beneficial for open-domain dialog system development.

Investigating the Impact of Pre-trained Language Models on Dialog Evaluation

no code yet • 5 Oct 2021

Yet, the impact of different Pr-LMs on the performance of automatic metrics is not well-understood.

Enhancing Self-Disclosure In Neural Dialog Models By Candidate Re-ranking

no code yet • 10 Sep 2021

One such area is of open-domain dialog modelling, neural dialog models based on GPT-2 such as DialoGPT have shown promising performance in single-turn conversation.

REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation

no code yet • 30 May 2021

We first clarify an assumption on reference-based metrics that, if more high-quality references are added into the reference set, the reliability of the metric will increase.

Discovering Dialog Structure Graph for Open-Domain Dialog Generation

no code yet • 31 Dec 2020

Learning interpretable dialog structure from human-human dialogs yields basic insights into the structure of conversation, and also provides background knowledge to facilitate dialog generation.