Chatbots, Humbots, and the Quest for Artificial General Intelligence

@article{Grudin2019ChatbotsHA,
  title={Chatbots, Humbots, and the Quest for Artificial General Intelligence},
  author={Jonathan T. Grudin and Richard David Jacques},
  journal={Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  year={2019}
}
  • J. Grudin, R. Jacques
  • Published 2 May 2019
  • Computer Science
  • Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
What began as a quest for artificial general intelligence branched into several pursuits, including intelligent assistants developed by tech companies and task-oriented chatbots that deliver more information or services in specific domains. Progress quickened with the spread of low-latency networking, then accelerated dramatically a few years ago. In 2016, task-focused chatbots became a centerpiece of machine intelligence, promising interfaces that are more engaging than robotic answering… 

Figures and Tables from this paper

Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems
TLDR
An end-to-end pipeline for processing unrecognized user utterances is presented, including a specifically-tailored clustering algorithm, a novel approach to cluster representative extrac-tion, and cluster naming.
Constructing Transparent QA Chatbot based on the Official Website Documents
TLDR
A framework to construct a transparent QA chatbot directly from organizations’ official websites and consists of interpretable dialogue flowcharts and a simple retrieval-based architecture, which can be used for actual services that require responsibility for their behaviors.
Increasing Diversity with Deep Reinforcement Learning for Chatbots
TLDR
This model applies a Policy Gradient method that maximizes the expected reward of generating the next utterance given a history of previous utterances, and shows an improvement in diversity up to 0.16 almost 10x higher than the model without RL, while keeping the responses relevant to the input message.
A Proposed Chatbot Framework for COVID-19
TLDR
A smart chatbot system that can communicate with people and provide them with answers about the COVID-19 and uses the pre-trained Google BERT language model to tackle the popular role of question answering.
When There is No Progress with a Task-Oriented Chatbot: A Conversation Analysis
TLDR
A conversation analysis on a three-month conversation log of users conversing with a chatbot of a banking institution shows that users more often failed to make a progress in a conversation when they requested information than when they provided information.
User Expectations of Conversational Chatbots Based on Online Reviews
TLDR
Drawing from reviews of chatbots posted on Google Play, user experience and expectations of these agents are explored in a mixed-method study, revealing which social qualities of chatbot are the most significant for user satisfaction.
A survey on construction and enhancement methods in service chatbots design
TLDR
This survey aims to provide a comprehensive review of chatbots construction and enhancement methods, and introduces major techniques for the three core design philosophies, which are rule-based, retrieval-based and generation-based methods.
Insightful Assistant: AI-compatible Operation Graph Representations for Enhancing Industrial Conversational Agents
TLDR
Insightful Assistant---a pipeline concept based on a novel operation graph representation resulting from the intents detected, which achieves an accuracy of up to 95.0% (74.5%) for simple (complex) request detection with different variants and a top3-accuracy up to95.4% for data-/user-adaptive visualization.
Multi-Modal Repairs of Conversational Breakdowns in Task-Oriented Dialogs
TLDR
SOVITE is a new multi-modal speech plus direct manipulation interface that helps users discover, identify the causes of, and recover from conversational breakdowns using the resources of existing mobile app GUIs for grounding.
DIA: A Human AI Hybrid Conversational Assistant for Developing Contexts
TLDR
DIA is a human-chatbot (humbot) hybrid system that organically learns topic-specific knowledge and local language from user interactions that can help build a data-set of a topic and language-specific dialogues and collect survey data for through conversational interaction.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 60 REFERENCES
From Eliza to XiaoIce: challenges and opportunities with social chatbots
TLDR
The success metric for social chatbots is defined as conversation-turns per session (CPS), and it is shown how XiaoIce can dynamically recognize emotion and engage the user throughout long conversations with appropriate interpersonal responses.
CoChat: Enabling Bot and Human Collaboration for Task Completion
TLDR
This paper introduces CoChat, a dialog management framework to enable effective collaboration between bots and human workers, and proposes a memory-enhanced hierarchical RNN (MemHRNN) to handle the one-shot learning challenges caused by instantly introducing new actions in CoChat.
Evaluating and Informing the Design of Chatbots
TLDR
A study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface.
Agents that reduce work and information overload
TLDR
Results from several prototype agents that have been built using an approach to building interface agents are presented, including agents that provide personalized assistance with meeting scheduling, email handling, electronic news filtering, and selection of entertainment.
All Work and No Play? Conversations with a Question-and-Answer Chatbot in the Wild
TLDR
By studying a field deployment of a Human Resource chatbot, data is reported on users' interest areas in conversational interactions to inform the development of CAs, and rich signals in Conversational interactions are highlighted for inferring user satisfaction with the instrumental usage and playful interactions with the agent.
"Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents
TLDR
This paper reports the findings of interviews with 14 users of CAs in an effort to understand the current interactional factors affecting everyday use, and finds user expectations dramatically out of step with the operation of the systems.
All Work and No Play?
TLDR
By studying a field deployment of a Human Resource chatbot, data is reported on users' interest areas in conversational interactions to inform the development of CAs, and rich signals in Conversational interactions are highlighted for inferring user satisfaction with the instrumental usage and playful interactions with the agent.
Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop
TLDR
The iterative approach used to develop Calendar.help is described, which provides insight into how complex information tasks can be broken down into repeatable components that can be executed efficiently to improve productivity.
I'm Sorry, Dave, I'm Afraid I Can't Do That: Chatbot Perception and Expectations
TLDR
This study includes qualitative data from 54 participants in the US and India, sharing their expectations and experiences with a chatbot, to understand user perception and expectations of chatbots and identify domains where chatbots can add meaningful purpose.
...
1
2
3
4
5
...