• Corpus ID: 220128003

Dialog as a Vehicle for Lifelong Learning

@article{Padmakumar2020DialogAA,
  title={Dialog as a Vehicle for Lifelong Learning},
  author={Aishwarya Padmakumar and Raymond J. Mooney},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.14767}
}
Dialog systems research has primarily been focused around two main types of applications - task-oriented dialog systems that learn to use clarification to aid in understanding a goal, and open-ended dialog systems that are expected to carry out unconstrained "chit chat" conversations. However, dialog interactions can also be used to obtain various types of knowledge that can be used to improve an underlying language understanding system, or other machine learning systems that the dialog acts… 
2 Citations

Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

TLDR
This work builds and deploy a role-playing game, whereby human players converse with learning agents situated in an open-domain fantasy world and shows that by training models on the conversations they have with humans in the game the models progressively improve, as measured by automatic metrics and online engagement scores.

References

SHOWING 1-10 OF 41 REFERENCES

A Network-based End-to-End Trainable Task-oriented Dialogue System

TLDR
This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Learning environmental knowledge from task-based human-robot dialog

TLDR
The approach is flexible to the ways that untrained people interact with robots, is robust to speech to text errors and is able to learn referring expressions for physical locations in a map, thereby enabling more effective and intuitive human robot dialog.

Learning to Interpret Natural Language Commands through Human-Robot Dialog

TLDR
This work introduces a dialog agent for mobile robots that understands human instructions through semantic parsing, actively resolves ambiguities using a dialog manager, and incrementally learns from human-robot conversations by inducing training data from user paraphrases.

Vision-and-Dialog Navigation

TLDR
This work introduces Cooperative Vision-and-Dialog Navigation, a dataset of over 2k embodied, human-human dialogs situated in simulated, photorealistic home environments and establishes an initial, multi-modal sequence-to-sequence model.

POMDP-Based Statistical Spoken Dialog Systems: A Review

TLDR
This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

TLDR
The recently proposed hierarchical recurrent encoder-decoder neural network is extended to the dialogue domain, and it is demonstrated that this model is competitive with state-of-the-art neural language models and back-off n-gram models.

Training an adaptive dialogue policy for interactive learning of visually grounded word meanings

TLDR
The overall performance of the learning agent is affected by who takes initiative in the dialogues, and the ability to express/use their confidence level about visual attributes, and an adaptive dialogue policy is trained which optimises the trade-off between classifier accuracy and tutoring costs.

Roving Mind: a balancing act between open–domain and engaging dialogue systems

TLDR
Roving Mind is described, a dialogue system which combines domain– independence with a modular architecture for open–domain spoken conversation, with a specific module for user engagement, and finds a correlation between cumulative sentiment and user ratings.

Learning how to Learn: An Adaptive Dialogue Agent for Incrementally Learning Visually Grounded Word Meanings

TLDR
An optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data, and finds a better trade-off between classifier accuracy and tutoring costs than hand-crafted rule-based policies, including ones with dynamic policies.

Toward an Architecture for Never-Ending Language Learning

TLDR
This work proposes an approach and a set of design principles for an intelligent computer agent that runs forever and describes a partial implementation of such a system that has already learned to extract a knowledge base containing over 242,000 beliefs.