%0 Conference Paper %1 pethe-etal-2020-chapter %A Pethe, Charuta %A Kim, Allen %A Skiena, Steve %B Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) %C Online %D 2020 %I Association for Computational Linguistics %K events nlp scenedetection scenes %P 8373--8383 %R 10.18653/v1/2020.emnlp-main.672 %T Chapter Captor: Text Segmentation in Novels %U https://aclanthology.org/2020.emnlp-main.672 %X Books are typically segmented into chapters and sections, representing coherent sub-narratives and topics. We investigate the task of predicting chapter boundaries, as a proxy for the general task of segmenting long texts. We build a Project Gutenberg chapter segmentation data set of 9,126 English novels, using a hybrid approach combining neural inference and rule matching to recognize chapter title headers in books, achieving an F1-score of 0.77 on this task. Using this annotated data as ground truth after removing structural cues, we present cut-based and neural methods for chapter segmentation, achieving a F1-score of 0.453 on the challenging task of exact break prediction over book-length documents. Finally, we reveal interesting historical trends in the chapter structure of novels.

@inproceedings{pethe-etal-2020-chapter, abstract = {Books are typically segmented into chapters and sections, representing coherent sub-narratives and topics. We investigate the task of predicting chapter boundaries, as a proxy for the general task of segmenting long texts. We build a Project Gutenberg chapter segmentation data set of 9,126 English novels, using a hybrid approach combining neural inference and rule matching to recognize chapter title headers in books, achieving an F1-score of 0.77 on this task. Using this annotated data as ground truth after removing structural cues, we present cut-based and neural methods for chapter segmentation, achieving a F1-score of 0.453 on the challenging task of exact break prediction over book-length documents. Finally, we reveal interesting historical trends in the chapter structure of novels.}, added-at = {2021-07-12T16:14:45.000+0200}, address = {Online}, author = {Pethe, Charuta and Kim, Allen and Skiena, Steve}, biburl = {https://www.bibsonomy.org/bibtex/2885d0b2ef872348d36876c328c647b9d/albinzehe}, booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, doi = {10.18653/v1/2020.emnlp-main.672}, interhash = {c2ec26b72708960eef8ff522db7eebaa}, intrahash = {885d0b2ef872348d36876c328c647b9d}, keywords = {events nlp scenedetection scenes}, month = nov, pages = {8373--8383}, publisher = {Association for Computational Linguistics}, timestamp = {2021-07-12T16:14:52.000+0200}, title = {{C}hapter {C}aptor: {T}ext {S}egmentation in {N}ovels}, url = {https://aclanthology.org/2020.emnlp-main.672}, year = 2020 }