%0 Conference Paper %1 muzny2017twostage %A Muzny, Grace %A Fang, Michael %A Chang, Angel %A Jurafsky, Dan %B Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers %C Valencia, Spain %D 2017 %I Association for Computational Linguistics %K acl citation extraction language natural nlp processing quotation quote %P 460--470 %T A Two-stage Sieve Approach for Quote Attribution %U https://www.aclweb.org/anthology/E17-1044 %X We present a deterministic sieve-based system for attributing quotations in literary text and a new dataset: QuoteLi3. Quote attribution, determining who said what in a given text, is important for tasks like creating dialogue systems, and in newer areas like computational literary studies, where it creates opportunities to analyze novels at scale rather than only a few at a time. We release QuoteLi3, which contains more than 6,000 annotations linking quotes to speaker mentions and quotes to speaker entities, and introduce a new algorithm for quote attribution. Our two-stage algorithm first links quotes to mentions, then mentions to entities. Using two stages encapsulates difficult sub-problems and improves system performance. The modular design allows us to tune for overall performance or higher precision, which is useful for many real-world use cases. Our system achieves an average F-score of 87.5 across three novels, outperforming previous systems, and can be tuned for precision of 90.4 at a recall of 65.1.

@inproceedings{muzny2017twostage, abstract = {We present a deterministic sieve-based system for attributing quotations in literary text and a new dataset: QuoteLi3. Quote attribution, determining who said what in a given text, is important for tasks like creating dialogue systems, and in newer areas like computational literary studies, where it creates opportunities to analyze novels at scale rather than only a few at a time. We release QuoteLi3, which contains more than 6,000 annotations linking quotes to speaker mentions and quotes to speaker entities, and introduce a new algorithm for quote attribution. Our two-stage algorithm first links quotes to mentions, then mentions to entities. Using two stages encapsulates difficult sub-problems and improves system performance. The modular design allows us to tune for overall performance or higher precision, which is useful for many real-world use cases. Our system achieves an average F-score of 87.5 across three novels, outperforming previous systems, and can be tuned for precision of 90.4 at a recall of 65.1.}, added-at = {2020-10-20T11:50:26.000+0200}, address = {Valencia, Spain}, author = {Muzny, Grace and Fang, Michael and Chang, Angel and Jurafsky, Dan}, biburl = {https://www.bibsonomy.org/bibtex/205eb128a7b91cc0d95cc1d4ccc8a3f00/jaeschke}, booktitle = {Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, description = {A Two-stage Sieve Approach for Quote Attribution - ACL Anthology}, interhash = {2580e5376aa876365073103389245658}, intrahash = {05eb128a7b91cc0d95cc1d4ccc8a3f00}, keywords = {acl citation extraction language natural nlp processing quotation quote}, month = apr, pages = {460--470}, publisher = {Association for Computational Linguistics}, timestamp = {2020-10-20T11:50:26.000+0200}, title = {A Two-stage Sieve Approach for Quote Attribution}, url = {https://www.aclweb.org/anthology/E17-1044}, year = 2017 }