This paper focuses on the computational identification of characters in fictional narratives, regardless of their nature, i.e., either humans, animals or other type of beings. We approach this problem as a supervised binary classification task, whether or not a noun in a narrative -specifically in a fairy taleis classified as a character. A wide range of Machine Learning algorithms and configurations were tested in order to come up with the most appropriate model (or set of models) to successfully fulfil this task. Despite the challenges associated with the character identification in the domain of children stories, the best models obtain an F-Measure above 0.80, proving a good performance and broadly outperforming the baselines.
Description
Tackling the Challenge of Computational Identification of Characters in Fictional Narratives - IEEE Conference Publication
%0 Conference Paper
%1 8816908
%A Barros, Cristina
%A Vicente, Marta Esther
%A Lloret, Elena
%B 2019 IEEE International Conference on Cognitive Computing (ICCC)
%D 2019
%E Bertino, Elisa
%E Chang, Carl K.
%E Chen, Peter
%E Damiani, Ernesto
%E Goul, Michael
%E Oyama, Katsunori
%K character fiction identification literature nlp
%P 122-129
%R 10.1109/ICCC.2019.00031
%T Tackling the Challenge of Computational Identification of Characters in Fictional Narratives.
%U https://ieeexplore.ieee.org/abstract/document/8816908
%X This paper focuses on the computational identification of characters in fictional narratives, regardless of their nature, i.e., either humans, animals or other type of beings. We approach this problem as a supervised binary classification task, whether or not a noun in a narrative -specifically in a fairy taleis classified as a character. A wide range of Machine Learning algorithms and configurations were tested in order to come up with the most appropriate model (or set of models) to successfully fulfil this task. Despite the challenges associated with the character identification in the domain of children stories, the best models obtain an F-Measure above 0.80, proving a good performance and broadly outperforming the baselines.
@inproceedings{8816908,
abstract = {This paper focuses on the computational identification of characters in fictional narratives, regardless of their nature, i.e., either humans, animals or other type of beings. We approach this problem as a supervised binary classification task, whether or not a noun in a narrative -specifically in a fairy taleis classified as a character. A wide range of Machine Learning algorithms and configurations were tested in order to come up with the most appropriate model (or set of models) to successfully fulfil this task. Despite the challenges associated with the character identification in the domain of children stories, the best models obtain an F-Measure above 0.80, proving a good performance and broadly outperforming the baselines.},
added-at = {2020-03-11T15:44:44.000+0100},
author = {Barros, Cristina and Vicente, Marta Esther and Lloret, Elena},
biburl = {https://www.bibsonomy.org/bibtex/28cbb0e3fde674b22d79289e9225c3119/schwemmlein},
booktitle = {2019 IEEE International Conference on Cognitive Computing (ICCC)},
description = {Tackling the Challenge of Computational Identification of Characters in Fictional Narratives - IEEE Conference Publication},
doi = {10.1109/ICCC.2019.00031},
editor = {Bertino, Elisa and Chang, Carl K. and Chen, Peter and Damiani, Ernesto and Goul, Michael and Oyama, Katsunori},
interhash = {e3642266b2720685a2cec8aba44ff6e8},
intrahash = {8cbb0e3fde674b22d79289e9225c3119},
issn = {null},
keywords = {character fiction identification literature nlp},
month = {July},
pages = {122-129},
timestamp = {2020-03-11T15:44:44.000+0100},
title = {Tackling the Challenge of Computational Identification of Characters in Fictional Narratives.},
url = {https://ieeexplore.ieee.org/abstract/document/8816908},
year = 2019
}