Toward Gender-Inclusive Coreference Resolution
作者： Hal Daumé , Yang Trista Cao
DOI: 10.18653/V1/2020.ACL-MAIN.418
关键词:
摘要: Correctly resolving textual mentions of people fundamentally entails making inferences about those people. Such raise the risk systemic biases in coreference resolution systems, including that can harm binary and non-binary trans cis stakeholders. To better understand such biases, we foreground nuanced conceptualizations gender from sociology sociolinguistics, develop two new datasets for interrogating bias crowd annotations existing systems. Through these studies, conducted on English text, confirm without acknowledging building systems recognize complexity gender, build lead to many potential harms.
acl2020.org参考文章(190)
Vinodkumar Prabhakaran, Emily E. Reid, Owen Rambow, Gender and Power: How Gender and Gender Environment Affect Manifestations of Power empirical methods in natural language processing. pp. 1965- 1976 ,(2014) , 10.3115/V1/D14-1211
Marion Weller, Alexander Fraser, Sabine Schulte im Walde, Using subcategorization knowledge to improve case prediction for translation to German meeting of the association for computational linguistics. pp. 593- 603 ,(2013)
Goran Glavaš, Jan Šnajder, Damir Korenċić, Aspect-Oriented Opinion Mining from User Reviews in Croatian meeting of the association for computational linguistics. pp. 18- 23 ,(2013)
Naho Orita, Eliana Vornov, Naomi Feldman, Hal Daumé III, Why discourse affects speakers' choice of referring expressions Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). ,vol. 1, pp. 1639- 1649 ,(2015) , 10.3115/V1/P15-1158
Stefan Ultes, Alexander Schmitt, Maxim Sidorov, Comparison of Gender- and Speaker-adaptive Emotion Recognition language resources and evaluation. pp. 3476- 3480 ,(2014)
Anil Ramakrishna, Nikolaos Malandrakis, Elizabeth Staruk, Shrikanth Narayanan, A quantitative analysis of gender differences in movies using psycholinguistic normatives empirical methods in natural language processing. pp. 1996- 2001 ,(2015) , 10.18653/V1/D15-1234
Yuanchao Liu, Ming Liu, Xiaolong Wang, Limin Wang, Jingjing Li, None, PAL: A Chatterbot System for Answering Domain-specific Questions meeting of the association for computational linguistics. pp. 67- 72 ,(2013)
Chen Chen, Vincent Ng, Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 763- 774 ,(2014) , 10.3115/V1/D14-1084
Anders Johannsen, Dirk Hovy, Anders Søgaard, Cross-lingual syntactic variation over age and gender conference on computational natural language learning. pp. 103- 112 ,(2015) , 10.18653/V1/K15-1011
Smruthi Mukund, Rohini Srihari, Debanjan Ghosh, Using Sequence Kernels to identify Opinion Entities in Urdu conference on computational natural language learning. pp. 58- 67 ,(2011)