Baruah, Sabyasachee; Chakravarthula, Sandeep Nallan; Narayanan, Shrikanth Annotation and Evaluation of Coreference Resolution in Screenplays Inproceedings pp. 2004–2010, Association for Computational Linguistics, 2021. Abstract | Links | BibTeX | Tags: coreference resolution @inproceedings{baruah-etal-2021-annotation,
title = {Annotation and Evaluation of Coreference Resolution in Screenplays},
author = {Sabyasachee Baruah and Sandeep Nallan Chakravarthula and Shrikanth Narayanan},
doi = {10.18653/v1/2021.findings-acl.176},
year = {2021},
date = {2021-08-02},
pages = {2004–2010},
publisher = {Association for Computational Linguistics},
abstract = {Screenplays refer to characters using different names, pronouns, and nominal expressions. We need to resolve these mentions to
the correct referent character for better story understanding and holistic research in computational narratology. Coreference resolution of character mentions in screenplays becomes
challenging because of the large document lengths, unique structural features like scene headers, interleaving of action and speech
passages, and reliance on the accompanying video. In this work, we first adapt widely used annotation guidelines to address domain-specific issues in screenplays. We develop an automatic screenplay parser to extract the
structural information and design coreference rules based upon the structure. Our model exploits these structural features and outperforms a benchmark coreference model on the
screenplay coreference resolution task.},
keywords = {coreference resolution},
pubstate = {published},
tppubtype = {inproceedings}
}
Screenplays refer to characters using different names, pronouns, and nominal expressions. We need to resolve these mentions to
the correct referent character for better story understanding and holistic research in computational narratology. Coreference resolution of character mentions in screenplays becomes
challenging because of the large document lengths, unique structural features like scene headers, interleaving of action and speech
passages, and reliance on the accompanying video. In this work, we first adapt widely used annotation guidelines to address domain-specific issues in screenplays. We develop an automatic screenplay parser to extract the
structural information and design coreference rules based upon the structure. Our model exploits these structural features and outperforms a benchmark coreference model on the
screenplay coreference resolution task. |
