发布求助
文献互助 智能选刊 最新文献

Proceedings of the First Workshop on Gender Bias in Natural Language Processing最新文献

筛选
英文 中文
The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations 保护类词表在语境化词表示的偏见识别中的作用
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-3808
João Sedoc, L. Ungar
{"title":"The Role of Protected Class Word Lists in Bias Identification of Contextualized Word Representations","authors":"João Sedoc, L. Ungar","doi":"10.18653/v1/W19-3808","DOIUrl":"https://doi.org/10.18653/v1/W19-3808","url":null,"abstract":"Systemic bias in word embeddings has been widely reported and studied, and efforts made to debias them; however, new contextualized embeddings such as ELMo and BERT are only now being similarly studied. Standard debiasing methods require heterogeneous lists of target words to identify the “bias subspace”. We show show that using new contextualized word embeddings in conceptor debiasing allows us to more accurately debias word embeddings by breaking target word lists into more homogeneous subsets and then combining (”Or’ing”) the debiasing conceptors of the different subsets.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"27 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120854093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
Automatic Gender Identification and Reinflection in Arabic 阿拉伯语自动性别识别和反映
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 2019-08-01 DOI: 10.18653/v1/W19-3822
Nizar Habash, Houda Bouamor, Christine Chung
{"title":"Automatic Gender Identification and Reinflection in Arabic","authors":"Nizar Habash, Houda Bouamor, Christine Chung","doi":"10.18653/v1/W19-3822","DOIUrl":"https://doi.org/10.18653/v1/W19-3822","url":null,"abstract":"The impressive progress in many Natural Language Processing (NLP) applications has increased the awareness of some of the biases these NLP systems have with regards to gender identities. In this paper, we propose an approach to extend biased single-output gender-blind NLP systems with gender-specific alternative reinflections. We focus on Arabic, a gender-marking morphologically rich language, in the context of machine translation (MT) from English, and for first-person-singular constructions only. Our contributions are the development of a system-independent gender-awareness wrapper, and the building of a corpus for training and evaluating first-person-singular gender identification and reinflection in Arabic. Our results successfully demonstrate the viability of this approach with 8% relative increase in Bleu score for first-person-singular feminine, and 5.3% comparable increase for first-person-singular masculine on top of a state-of-the-art gender-blind MT system on a held-out test set.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131906505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 32
Fill the GAP: Exploiting BERT for Pronoun Resolution 填补空白:利用BERT来解决代词问题
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 2019-07-29 DOI: 10.18653/v1/W19-3815
Kai-Chou Yang, Timothy Niven, Tzu-Hsuan Chou, Hung-Yu kao
{"title":"Fill the GAP: Exploiting BERT for Pronoun Resolution","authors":"Kai-Chou Yang, Timothy Niven, Tzu-Hsuan Chou, Hung-Yu kao","doi":"10.18653/v1/W19-3815","DOIUrl":"https://doi.org/10.18653/v1/W19-3815","url":null,"abstract":"In this paper, we describe our entry in the gendered pronoun resolution competition which achieved fourth place without data augmentation. Our method is an ensemble system of BERTs which resolves co-reference in an interaction space. We report four insights from our work: BERT’s representations involve significant redundancy; modeling interaction effects similar to natural language inference models is useful for this task; there is an optimal BERT layer to extract representations for pronoun resolution; and the difference between the attention weights from the pronoun to the candidate entities was highly correlated with the correct label, with interesting implications for future work.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131722708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
BERT Masked Language Modeling for Co-reference Resolution 共同引用解析的BERT掩码语言建模
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3811
Felipe Alfaro, M. Costa-jussà, José A. R. Fonollosa
{"title":"BERT Masked Language Modeling for Co-reference Resolution","authors":"Felipe Alfaro, M. Costa-jussà, José A. R. Fonollosa","doi":"10.18653/v1/W19-3811","DOIUrl":"https://doi.org/10.18653/v1/W19-3811","url":null,"abstract":"This paper explains the TALP-UPC participation for the Gendered Pronoun Resolution shared-task of the 1st ACL Workshop on Gender Bias for Natural Language Processing. We have implemented two models for mask language modeling using pre-trained BERT adjusted to work for a classification problem. The proposed solutions are based on the word probabilities of the original BERT model, but using common English names to replace the original test names.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122167708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
Gendered Ambiguous Pronoun (GAP) Shared Task at the Gender Bias in NLP Workshop 2019 性别歧义代词(GAP)在2019年NLP性别偏见研讨会上的共同任务
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3801
Kellie Webster, M. Costa-jussà, Christian Hardmeier, Will Radford
{"title":"Gendered Ambiguous Pronoun (GAP) Shared Task at the Gender Bias in NLP Workshop 2019","authors":"Kellie Webster, M. Costa-jussà, Christian Hardmeier, Will Radford","doi":"10.18653/v1/W19-3801","DOIUrl":"https://doi.org/10.18653/v1/W19-3801","url":null,"abstract":"The 1st ACL workshop on Gender Bias in Natural Language Processing included a shared task on gendered ambiguous pronoun (GAP) resolution. This task was based on the coreference challenge defined in Webster et al. (2018), designed to benchmark the ability of systems to resolve pronouns in real-world contexts in a gender-fair way. 263 teams competed via a Kaggle competition, with the winning system achieving logloss of 0.13667 and near gender parity. We review the approaches of eleven systems with accepted description papers, noting their effective use of BERT (Devlin et al., 2018), both via fine-tuning and for feature extraction, as well as ensembling.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131792013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 19
On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution 关于GAP共同参考决议共享任务:来自第三名解决方案的见解
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3816
Artem Abzaliev
{"title":"On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution","authors":"Artem Abzaliev","doi":"10.18653/v1/W19-3816","DOIUrl":"https://doi.org/10.18653/v1/W19-3816","url":null,"abstract":"This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123770394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Relating Word Embedding Gender Biases to Gender Gaps: A Cross-Cultural Analysis 词嵌入性别偏见与性别差距的跨文化分析
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3803
Scott Friedman, S. Schmer-Galunder, Anthony Chen, J. Rye
{"title":"Relating Word Embedding Gender Biases to Gender Gaps: A Cross-Cultural Analysis","authors":"Scott Friedman, S. Schmer-Galunder, Anthony Chen, J. Rye","doi":"10.18653/v1/W19-3803","DOIUrl":"https://doi.org/10.18653/v1/W19-3803","url":null,"abstract":"Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent bias in their training text. These biases are often sub-optimal and recent work poses methods to rectify them; however, these biases may shed light on actual racial or gender gaps in the culture(s) that produced the training text, thereby helping us understand cultural context through big data. This paper presents an approach for quantifying gender bias in word embeddings, and then using them to characterize statistical gender gaps in education, politics, economics, and health. We validate these metrics on 2018 Twitter data spanning 51 U.S. regions and 99 countries. We correlate state and country word embedding biases with 18 international and 5 U.S.-based statistical gender gaps, characterizing regularities and predictive strength.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126697506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
Transfer Learning from Pre-trained BERT for Pronoun Resolution 基于预训练BERT的代词解析迁移学习
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3812
Xingce Bao, Qianqian Qiao
{"title":"Transfer Learning from Pre-trained BERT for Pronoun Resolution","authors":"Xingce Bao, Qianqian Qiao","doi":"10.18653/v1/W19-3812","DOIUrl":"https://doi.org/10.18653/v1/W19-3812","url":null,"abstract":"The paper describes the submission of the team “We used bert!” to the shared task Gendered Pronoun Resolution (Pair pronouns to their correct entities). Our final submission model based on the fine-tuned BERT (Bidirectional Encoder Representations from Transformers) ranks 14th among 838 teams with a multi-class logarithmic loss of 0.208. In this work, contribution of transfer learning technique to pronoun resolution systems is investigated and the gender bias contained in classification models is evaluated.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125902015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 16
Proposed Taxonomy for Gender Bias in Text; A Filtering Methodology for the Gender Generalization Subtype 文本性别偏见的分类方法研究性别泛化子类型的过滤方法
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3802
Yasmeen Hitti, Eunbee Jang, I. Moreno, C. Pelletier
{"title":"Proposed Taxonomy for Gender Bias in Text; A Filtering Methodology for the Gender Generalization Subtype","authors":"Yasmeen Hitti, Eunbee Jang, I. Moreno, C. Pelletier","doi":"10.18653/v1/W19-3802","DOIUrl":"https://doi.org/10.18653/v1/W19-3802","url":null,"abstract":"The purpose of this paper is to present an empirical study on gender bias in text. Current research in this field is focused on detecting and correcting for gender bias in existing machine learning models rather than approaching the issue at the dataset level. The underlying motivation is to create a dataset which could enable machines to learn to differentiate bias writing from non-bias writing. A taxonomy is proposed for structural and contextual gender biases which can manifest themselves in text. A methodology is proposed to fetch one type of structural gender bias, Gender Generalization. We explore the IMDB movie review dataset and 9 different corpora from Project Gutenberg. By filtering out irrelevant sentences, the remaining pool of candidate sentences are sent for human validation. A total of 6123 judgments are made on 1627 sentences and after a quality check on randomly selected sentences we obtain an accuracy of 75%. Out of the 1627 sentences, 808 sentence were labeled as Gender Generalizations. The inter-rater reliability amongst labelers was of 61.14%.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129838315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 26
Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories 跨领域词嵌入中的性别偏见测量和发现新的性别偏见词类
Proceedings of the First Workshop on Gender Bias in Natural Language Processing Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-3804
K. Chaloner, Alfredo Maldonado
{"title":"Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories","authors":"K. Chaloner, Alfredo Maldonado","doi":"10.18653/v1/W19-3804","DOIUrl":"https://doi.org/10.18653/v1/W19-3804","url":null,"abstract":"Prior work has shown that word embeddings capture human stereotypes, including gender bias. However, there is a lack of studies testing the presence of specific gender bias categories in word embeddings across diverse domains. This paper aims to fill this gap by applying the WEAT bias detection method to four sets of word embeddings trained on corpora from four different domains: news, social networking, biomedical and a gender-balanced corpus extracted from Wikipedia (GAP). We find that some domains are definitely more prone to gender bias than others, and that the categories of gender bias present also vary for each set of word embeddings. We detect some gender bias in GAP. We also propose a simple but novel method for discovering new bias categories by clustering word embeddings. We validate this method through WEAT’s hypothesis testing mechanism and find it useful for expanding the relatively small set of well-known gender bias word categories commonly used in the literature.","PeriodicalId":319066,"journal":{"name":"Proceedings of the First Workshop on Gender Bias in Natural Language Processing","volume":"75 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120899206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 42
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书