# Towards Learning Through Open-Domain Dialog

arXiv: https://arxiv.org/abs/2202.03040 · HTML: https://mlsanity.com/paper/2202.03040/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 7 Feb 2022.

## Builds on (most cited first, 10 of 10)

- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [Neural Open Information Extraction](https://mlsanity.com/paper/1805.04270/) (2018)
- [A Deep Reinforcement Learning Chatbot](https://mlsanity.com/paper/1709.02349/) (2017)
- [Anaphora and Coreference Resolution: A Review](https://mlsanity.com/paper/1805.11824/) (2018)
- [TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems](https://mlsanity.com/paper/2012.12458/) (2020)
- [A Roadmap towards Machine Intelligence](https://mlsanity.com/paper/1511.08130/) (2015)
- [Ensemble-Based Deep Reinforcement Learning for Chatbots](https://mlsanity.com/paper/1908.10422/) (2019)
- [OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction](https://mlsanity.com/paper/2010.03147/) (2020)
- [Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings](https://mlsanity.com/paper/1709.10423/) (2017)

## Abstract (arXiv)

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. However, research in this area is practically nonexistent. In this paper, we identify the modifications required for a dialog system to be able to learn from the dialog and propose generic approaches that can be used to implement those modifications. More specifically, we discuss how knowledge can be extracted from the dialog, used to update the agent's semantic network, and grounded in action and observation. This way, we hope to raise awareness for this subject, so that it can become a focus of research in the future.