Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cognitively Inspired Components for Social Conversational Agents

Alex Clay, Eduardo Alonso, Esther Mondragón

TL;DR

Through computational facsimiles of semantic and episodic memory, emotion, working memory, and the ability to learn, it is possible to address both the technical and social problems encountered by CAs.

Abstract

Current conversational agents (CA) have seen improvement in conversational quality in recent years due to the influence of large language models (LLMs) like GPT3. However, two key categories of problem remain. Firstly there are the unique technical problems resulting from the approach taken in creating the CA, such as scope with retrieval agents and the often nonsensical answers of former generative agents. Secondly, humans perceive CAs as social actors, and as a result expect the CA to adhere to social convention. Failure on the part of the CA in this respect can lead to a poor interaction and even the perception of threat by the user. As such, this paper presents a survey highlighting a potential solution to both categories of problem through the introduction of cognitively inspired additions to the CA. Through computational facsimiles of semantic and episodic memory, emotion, working memory, and the ability to learn, it is possible to address both the technical and social problems encountered by CAs.

Cognitively Inspired Components for Social Conversational Agents

TL;DR

Through computational facsimiles of semantic and episodic memory, emotion, working memory, and the ability to learn, it is possible to address both the technical and social problems encountered by CAs.

Abstract

Current conversational agents (CA) have seen improvement in conversational quality in recent years due to the influence of large language models (LLMs) like GPT3. However, two key categories of problem remain. Firstly there are the unique technical problems resulting from the approach taken in creating the CA, such as scope with retrieval agents and the often nonsensical answers of former generative agents. Secondly, humans perceive CAs as social actors, and as a result expect the CA to adhere to social convention. Failure on the part of the CA in this respect can lead to a poor interaction and even the perception of threat by the user. As such, this paper presents a survey highlighting a potential solution to both categories of problem through the introduction of cognitively inspired additions to the CA. Through computational facsimiles of semantic and episodic memory, emotion, working memory, and the ability to learn, it is possible to address both the technical and social problems encountered by CAs.
Paper Structure (15 sections, 4 equations, 3 figures)

This paper contains 15 sections, 4 equations, 3 figures.

Table of Contents

  1. Introduction
  2. Conversational Agents: The Technical Problem
  3. Retrieval Conversational Agents
  4. Generative Conversational Agents
  5. Computers As Social Actors: The Social Problem
  6. Anthropomorphism
  7. Believability
  8. Cognitively Inspired Additions: A Proposed Solution
  9. Semantic Memory
  10. Episodic Memory
  11. Working Memory
  12. Emotion
  13. Empathy
  14. Learning from Experience
  15. Conclusion

Figures (3)

  • Figure 1: Transformer architecture, which can possess any number of encoders and decoders, the original paper used 6 of each vaswani-2017.
  • Figure 2: BERT Token Embeddings, depending on the pre-training of the embeddings, such models can be used to translate between languages or generate a response to a given input devlin-2019.
  • Figure 3: BART framework: BART contains both Bidirectional Encoder, characteristic of BERT, and an auto-regressive decoder, characteristic of GPT lewis-2019.