2026-07-26T04:38:49Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:4769 2024-03-06T10:29:40Z ddc:004 open_access

Identifying and inferring objects from textual descriptions of scenes from books Cropper, Andrew Text-to-Scene Conversion Natural Language Processing Artificial Intelligence Fiction authors rarely provide detailed descriptions of scenes, preferring the reader to fill in the details using their imagination. Therefore, to perform detailed text-to-scene conversion from books, we need to not only identify explicit objects but also infer implicit objects. In this paper, we describe an approach to inferring objects using Wikipedia and WordNet. In our experiments, we are able to infer implicit objects such as monitor and computer by identifying explicit objects such as keyboard. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Andrew Cropper 2014 Is Part Of OASIcs, Volume 43, 2014 Imperial College Computing Student Workshop InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.ICCSW.2014.19 urn:nbn:de:0030-drops-47690 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ICCSW.2014.19 eng https://creativecommons.org/licenses/by/3.0/legalcode