%0 Conference Paper %1 Alpizar_Chacon_2020 %A Alpizar-Chacon, Isaac %A Sosnovsky, Sergey %B Proceedings of the ACM Symposium on Document Engineering 2020 %D 2020 %I ACM %K concept-extraction electronic-textbook text-analysis %P 1-10 %R 10.1145/3395027.3419585 %T Order out of Chaos: Construction of Knowledge Models from PDF Textbooks %U https://doi.org/10.1145%2F3395027.3419585 %X Textbooks are educational documents created, structured and formatted by domain experts with the main purpose to explain the knowledge in the domain to a novice. Authors use their understanding of the domain when structuring and formatting the content of a textbook to facilitate this explanation. As a result, the formatting and structural elements of textbooks carry the elements of domain knowledge implicitly encoded by their authors. Our paper presents an extendable approach towards automated extraction of this knowledge from textbooks taking into account their formatting rules and internal structure. We focus on PDF as the most common textbook representation format; however, the overall method is applicable to other formats as well. The evaluation experiments examine the accuracy of the approach, as well as the pragmatic quality of the obtained knowledge models using one of their possible applications -- semantic linking of textbooks in the same domain. The results indicate high accuracy of model construction on symbolic, syntactic and structural levels across textbooks and domains, and demonstrate the added value of the extracted models on the semantic level.

@inproceedings{Alpizar_Chacon_2020, abstract = {Textbooks are educational documents created, structured and formatted by domain experts with the main purpose to explain the knowledge in the domain to a novice. Authors use their understanding of the domain when structuring and formatting the content of a textbook to facilitate this explanation. As a result, the formatting and structural elements of textbooks carry the elements of domain knowledge implicitly encoded by their authors. Our paper presents an extendable approach towards automated extraction of this knowledge from textbooks taking into account their formatting rules and internal structure. We focus on PDF as the most common textbook representation format; however, the overall method is applicable to other formats as well. The evaluation experiments examine the accuracy of the approach, as well as the pragmatic quality of the obtained knowledge models using one of their possible applications -- semantic linking of textbooks in the same domain. The results indicate high accuracy of model construction on symbolic, syntactic and structural levels across textbooks and domains, and demonstrate the added value of the extracted models on the semantic level. }, added-at = {2020-10-01T17:31:37.000+0200}, author = {Alpizar-Chacon, Isaac and Sosnovsky, Sergey}, biburl = {https://www.bibsonomy.org/bibtex/24adbb3f7956af86689bdb615a777b519/brusilovsky}, booktitle = {Proceedings of the {ACM} Symposium on Document Engineering 2020}, description = {Order out of Chaos | Proceedings of the ACM Symposium on Document Engineering 2020}, doi = {10.1145/3395027.3419585}, interhash = {28d82b46f1aa4b2ba6bfca0b29bbf406}, intrahash = {4adbb3f7956af86689bdb615a777b519}, keywords = {concept-extraction electronic-textbook text-analysis}, month = sep, pages = {1-10}, publisher = {{ACM}}, timestamp = {2020-10-01T17:31:37.000+0200}, title = {Order out of Chaos: Construction of Knowledge Models from PDF Textbooks}, url = {https://doi.org/10.1145%2F3395027.3419585}, year = 2020 }