MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery

This paper introduces a novel approach for learning natural language descriptions of scenery in Minecraft. We apply techniques from Computer Vision and Natural Language Processing to create an AI framework called MineObserver for assessing the accuracy of learner-generated descriptions of science-re...

Full description

Saved in:
Bibliographic Details
Main Authors: Jay Mahajan, Samuel Hum, Jeff Ginger, H. Chad Lane
Format: Article
Language:English
Published: LibraryPress@UF 2022-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/130729
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271222326099968
author Jay Mahajan
Samuel Hum
Jeff Ginger
H. Chad Lane
author_facet Jay Mahajan
Samuel Hum
Jeff Ginger
H. Chad Lane
author_sort Jay Mahajan
collection DOAJ
description This paper introduces a novel approach for learning natural language descriptions of scenery in Minecraft. We apply techniques from Computer Vision and Natural Language Processing to create an AI framework called MineObserver for assessing the accuracy of learner-generated descriptions of science-related images. The ultimate purpose of the system is to automatically assess the accuracy of learner observations, written in natural language, made during science learning activities that take place in Minecraft. Eventually, MineObserver will be used as part of a pedagogical agent framework for providing in-game support for learning. Preliminary results are mixed, but promising with approximately 62% of images in our test set being properly classified by our image captioning approach. Broadly, our work suggests that computer vision techniques work as expected in Minecraft and can serve as a basis for assessing learner observations.
format Article
id doaj-art-e37bbf25787f4e198d8c316c6fc3fdf3
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2022-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-e37bbf25787f4e198d8c316c6fc3fdf32025-08-20T01:52:18ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622022-05-013510.32473/flairs.v35i.13072966928MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft ImageryJay Mahajan0Samuel Hum1Jeff Ginger2H. Chad Lane3University of Illinois at Urbana ChampaignUniversity of Illinois at Urbana ChampaignUniversity of Illinois at Urbana ChampaignUniversity of Illinois at Urbana ChampaignThis paper introduces a novel approach for learning natural language descriptions of scenery in Minecraft. We apply techniques from Computer Vision and Natural Language Processing to create an AI framework called MineObserver for assessing the accuracy of learner-generated descriptions of science-related images. The ultimate purpose of the system is to automatically assess the accuracy of learner observations, written in natural language, made during science learning activities that take place in Minecraft. Eventually, MineObserver will be used as part of a pedagogical agent framework for providing in-game support for learning. Preliminary results are mixed, but promising with approximately 62% of images in our test set being properly classified by our image captioning approach. Broadly, our work suggests that computer vision techniques work as expected in Minecraft and can serve as a basis for assessing learner observations.https://journals.flvc.org/FLAIRS/article/view/130729computer visionnatural language processingpedagogical agent
spellingShingle Jay Mahajan
Samuel Hum
Jeff Ginger
H. Chad Lane
MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
Proceedings of the International Florida Artificial Intelligence Research Society Conference
computer vision
natural language processing
pedagogical agent
title MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
title_full MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
title_fullStr MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
title_full_unstemmed MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
title_short MineObserver: A Deep Learning Framework for Assessing Natural Language Descriptions of Minecraft Imagery
title_sort mineobserver a deep learning framework for assessing natural language descriptions of minecraft imagery
topic computer vision
natural language processing
pedagogical agent
url https://journals.flvc.org/FLAIRS/article/view/130729
work_keys_str_mv AT jaymahajan mineobserveradeeplearningframeworkforassessingnaturallanguagedescriptionsofminecraftimagery
AT samuelhum mineobserveradeeplearningframeworkforassessingnaturallanguagedescriptionsofminecraftimagery
AT jeffginger mineobserveradeeplearningframeworkforassessingnaturallanguagedescriptionsofminecraftimagery
AT hchadlane mineobserveradeeplearningframeworkforassessingnaturallanguagedescriptionsofminecraftimagery