Hierarchy Identification for Automatically Generating Table-of-Contents

Erbs, Nicolai; Gurevych, Iryna; Zesch, Torsten

doi:10.17185/duepublico/72177

Tagungsbeitrag 2013 CC BY-NC-SA 3.0

Veröffentlicht

Hierarchy Identification for Automatically Generating Table-of-Contents

Erbs, Nicolai ; Gurevych, Iryna ; Zesch, Torsten

A table-of-contents (TOC) provides a quick reference to a document‘s content and structure. We present the first study on identifying the hierarchical structure for automatically generating a TOC using only textual features instead of structural hints e.g. from HTML-tags. We create two new datasets to evaluate our approaches for hierarchy identification. We find that our algorithm performs on a level that is sufficient for a fully automated system. For documents without given segment titles, we extend out work by automatically generating segment titles. We make the datasets and our experimental framework publicly available in order to foster future research in TOC generation.

Vorschau

Einordnung

Konferenz:: 9th International Conference on Recent Advances in Natural Language Processing, RANLP 2013, Hissar, Bulgaria; 9–11 September, 2013
Datum der Veröffentlichung:: 2013
URN:: urn:nbn:de:hbz:464-20211026-143912-7
DOI:: 10.17185/duepublico/72177
Sprache:: Englisch
Ressourcentyp:: Text
Kollektion:: E-Publikationen
Sachgruppen der Deutschen Nationalbibliographie:: 004 Informatik
Link URL:: https://www.aclweb.org/anthology/R13-1033
Einrichtung:: Fakultät für Ingenieurwissenschaften, Informatik und Angewandte Kognitionswissenschaft, Informatik, Sprachtechnologie
Informationen zur Erstveröffentlichung:: Erbs, N., Gurevych, I., Zesch, T. (2013) Hierarchy Identification for Automatically Generating Table-of-Contents. In: Proceedings of the International Conference Recent Advances in Natural Language Processing (RANLP 2013) / Ruslan Mitkov, Galia Angelova, Kalina Bontcheva (Editors), pp. 252-260. https://www.aclweb.org/anthology/R13-1033