Sabyasachee Baruah, Sandeep Nallan Chakravarthula, and Shrikanth Narayanan. Annotation and Evaluation of Coreference Resolution in Screenplays. In Proceedings of the Association for Computational Linguistics (ACL), pp. 2004–2010, Association for Computational Linguistics, 2021.

Download

(unavailable)

Abstract

Screenplays refer to characters using different names, pronouns, and nominal expressions. We need to resolve these mentions tothe correct referent character for better story understanding and holistic research in computational narratology. Coreference resolution of character mentions in screenplays becomeschallenging because of the large document lengths, unique structural features like scene headers, interleaving of action and speechpassages, 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 thestructural information and design coreference rules based upon the structure. Our model exploits these structural features and outperforms a benchmark coreference model on thescreenplay coreference resolution task.

BibTeX Entry

@inproceedings{baruah-etal-2021-annotation,
title = {Annotation and Evaluation of Coreference Resolution in Screenplays},
 booktitle = {Proceedings of the Association for Computational Linguistics (ACL)},
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}
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Nov 25, 2022 16:09:19