AINI-embodied conversation agent applicable for interactive games (original) (raw)

Towards a more natural and intelligent interface with embodied conversation agent

Proceedings of the 2006 international conference on Game research and development, 2006

Conversational agent also known as chatterbots are computer programs which are designed to converse like a human as much as their intelligent allows. In many ways, they are the embodiment of Turing's vision. The ability for computers to converse with human users using natural language would arguably increase their usefulness. Recent advances in Natural Language Processing (NLP) and Artificial Intelligence (AI) in general have advances this field in realizing the vision of a more humanoid interactive system. This paper presents and discusses the use of embodied conversation agent (ECA) for the imitation games. This paper also presents the technical design of our ECA and its performance. In the interactive media industry, it can also been observed that the ECA are getting popular.

How Players Speak to an Intelligent Game Character Using Natural Language Messages

Transactions of the Digital Games Research Association, 2018

AI-driven characters that learn directly from human input are rare in digital games, but recent advances in several fields of machine learning suggests that they may soon be much more feasible to create. This study explores the design space for interacting with such a character through natural language text dialogue. We conducted an observational study with 18 high school students, who played Minecraft alongside a Wizard of Oz prototype of a companion AI character that learned from their actions and inputs. In this paper, we report on an analysis of the 186 natural language messages that players sent to the character, and review key variations in syntax, function and writing style. We find that players’ behaviour and language was differentiated by the extent to which they expressed an anthropomorphic view of the AI character and the level of interest that they showed in interacting with it.

The design of interactive conversation agents

2008

Interactive conversation agents or CAs are computer programs or application software designed to simulate conversation with one or more human users in natural language. Providing CAs with knowledge, intelligence and humanoid interface has allowed them to be used in several practical applications. This paper presented the development and its performance of the interactive CAs called Artificial Intelligent Natural-language Identity or AINI.

A General Intelligence Oriented Architecture for Embodied Natural Language Processing

A software architecture is described which enables a virtual agent in an online virtual world to carry out simple English language interactions grounded in its perceptions and actions. The use of perceptions to guide anaphor resolution is discussed, along with the use of natural language generation to answer simple questions about the observed world. This architecture has been implemented within the larger PetBrain system, which is built on the OpenCog open-source AI software framework and architected based on the OpenCogPrime design for integrative AGI, and has previously been used for nonlinguistic intelligent behaviors such as imitation and reinforcement learning.

Designing Natural-Language Game Conversations

This paper reports on LabLabLab's three year experience in game-design oriented research on interactive dialogue with non-playing characters and developing natural-language conversational games. It explores the specific affordances and constraints of natural-language interaction for game conversations and offers strategies for their effective design. It also examines the general notion of conversational puzzle and proposes interface-agnostic design approaches founded on the concepts of cognitive conflict and conversational moves.

Requirements for Spoken Conversational Agents In Games

Term Paper in the GSLT-1 course Speech Technology, 2005

Spoken conversational systems have mainly been designed to collabo-rate with a user to solve a particular task, such as managing bank trans-actions or book travels. Now the development has reached a point where new areas of application may be possible, such as in digital ...

Designing an intelligent dialogue system for serious games

2012

Abstract The objective of our work is to design a conversational agent (chatterbot) capable of understanding natural language statements in a restricted semantic domain. This feature is intended to allow a natural dialogue with a learner, especially in the context of serious games. This conversational agent will be experimented in a serious game for training staff, by simulating a client.

Enhancing sentient embodied conversational agents with machine learning

Pattern Recognition Letters, 2020

Within the area of intelligent User Interfaces, we propose what we call Sentient Embodied Conversational Agents (SECAs): virtual characters able to engage users in complex conversations and to incorporate sentient capabilities similar to the ones humans have. This paper introduces SECAs together with their architecture and a publicly available software library that facilitates their inclusion in applications-such as educational and elder-care-requiring proactive and sensitive agent behaviours. In fact, we illustrate our proposal with a virtual tutor embedded in an educational application for children. The evaluation was performed in two stages: firstly, we tested a version with basic textual processing capabilities; and secondly, we evaluated a SECA with Machine-Learning-enhanced user understanding capabilities. The results show a significant improvement in users' perception of the agent's understanding capability. Indeed, the Response Error Rate decreased from 22.31% to 11.46% using ML techniques. Moreover, 99.33% of the participants consider the global experience of talking with the virtual tutor with sentient capabilities to be satisfactory.

English Education Game using Non-Player Character Based on Natural Language Processing

Procedia Computer Science, 2019

Game education is a game that aims for educational and entertainment. But the educational game is not popular to users. Therefore, it takes innovation and other ways to improve the educational game itself. Based on the current user survey, games that have dynamic elements such as artificial intelligence are sufficiently requested by users. For this reason, this study aims to build educational games that implement artificial intelligent (AI). In a game, AI is often implemented as Non-Player Character (NPC). The method used for NPCs in this game is based on the Natural Language Processing approach. This is so that the NPC can answer questions about English automatically. The results show that the educational game that has this NPC gets an average score above 75% of users. In addition, users also provide positive feedback on the game itself apart from the questionnaire. So it can be concluded that the presence of NPCs in educational games can increase user interest. With this new approach, it is hoped that it can also increase the popularity ranking of the educational game genre.