Automated Narrative Information Extraction Using Non-Linear Pipelines
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 4036-4036.
Abstract
Our research focuses on the problem of automatically acquiring structured narrative information from natural language. We have focused on character extraction and narrative role identification from a corpus of Slavic folktales. To address natural language processing (NLP) issues in this particular domain we have explored alternatives to linear pipelined architectures for information extraction, specifically the idea of feedback loops that allow feeding information produced by later modules of the pipeline back to earlier modules. We propose the use of domain knowledge to improve core NLP tasks and the overall performance of our system.
@inproceedings{ijcai2016p592,
title = {Automated Narrative Information Extraction Using Non-Linear Pipelines},
author = {Valls-Vargas, Josep},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {4036--4036},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/592},
}
TY - CPAPER TI - Automated Narrative Information Extraction Using Non-Linear Pipelines AU - Valls-Vargas, Josep T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 4036 EP - 4036 UR - https://ijcai.org/proceedings/2016/592 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
