Towards Understanding Gender Bias in Relation Extraction

Recent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction (AKBC). While much attention has been dedicated towards improvements in accuracy, there have been no attempts in the literature to our knowledge to evaluate social biases in NRE systems. We create WikiGenderBias, a distantly supervised dataset with a human annotated test set. WikiGenderBias has sentences specifically curated to analyze gender bias in relation extraction systems. We use WikiGenderBias to evaluate systems for bias and find that NRE systems exhibit gender biased predictions and lay groundwork for future evaluation of bias in NRE. We also analyze how name anonymization, hard debiasing for word embeddings, and counterfactual data augmentation affect gender bias in predictions and performance.

[1]  Anupam Datta,et al.  Gender Bias in Neural Natural Language Processing , 2018, Logic, Language, and Security.

[2]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[3]  Nello Cristianini,et al.  Classification using String Kernels , 2000 .

[4]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[5]  Rachel Rudinger,et al.  Gender Bias in Coreference Resolution , 2018, NAACL.

[6]  Ryan Cotterell,et al.  It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution , 2019, EMNLP.

[7]  Ryan Cotterell,et al.  Gender Bias in Contextualized Word Embeddings , 2019, NAACL.

[8]  Dmitry Zelenko,et al.  Kernel methods for relation extraction , 2003 .

[9]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[10]  Thomas A. Runkler,et al.  Neural Relation Extraction within and across Sentence Boundaries , 2019, AAAI.

[11]  Ralph Grishman,et al.  Extracting Relations with Integrated Information Using Kernel Methods , 2005, ACL.

[12]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[13]  Daniel Jurafsky,et al.  Word embeddings quantify 100 years of gender and ethnic stereotypes , 2017, Proceedings of the National Academy of Sciences.

[14]  Andrew McCallum,et al.  Modeling Relations and Their Mentions without Labeled Text , 2010, ECML/PKDD.

[15]  David Bamman,et al.  Adversarial Training for Relation Extraction , 2017, EMNLP.

[16]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[17]  Jieyu Zhao,et al.  Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints , 2017, EMNLP.

[18]  Maosong Sun,et al.  OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction , 2019, EMNLP.

[19]  悠太 菊池,et al.  大規模要約資源としてのNew York Times Annotated Corpus , 2015 .

[20]  Saif Mohammad,et al.  Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems , 2018, *SEMEVAL.

[21]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[22]  Patrick Pantel,et al.  Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations , 2006, ACL.

[23]  Nanyun Peng,et al.  The Woman Worked as a Babysitter: On Biases in Language Generation , 2019, EMNLP.

[24]  Seung-won Hwang,et al.  KBQA: Learning Question Answering over QA Corpora and Knowledge Bases , 2019, Proc. VLDB Endow..

[25]  J. Fleiss.  Measuring nominal scale agreement among many raters. , 1971 .

[26]  William Yang Wang,et al.  Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning , 2018, ACL.

[27]  Nguyen Bach,et al.  A Review of Relation Extraction , 2007 .

[28]  Jian Su,et al.  Exploring Various Knowledge in Relation Extraction , 2005, ACL.

[29]  Sergey Brin,et al.  Extracting Patterns and Relations from the World Wide Web , 1998, WebDB.

[30]  Zhifang Sui,et al.  A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction , 2017, EMNLP.

[31]  Doug Downey,et al.  Unsupervised named-entity extraction from the Web: An experimental study , 2005, Artif. Intell..

[32]  Ramesh Nallapati,et al.  Multi-instance Multi-label Learning for Relation Extraction , 2012, EMNLP.

[33]  Marta R. Costa-jussà,et al.  Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques , 2019, Proceedings of the First Workshop on Gender Bias in Natural Language Processing.

[34]  Jun Zhao,et al.  Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks , 2015, EMNLP.

[35]  Zhiyuan Liu,et al.  Neural Knowledge Acquisition via Mutual Attention Between Knowledge Graph and Text , 2018, AAAI.

[36]  Chiranjib Bhattacharyya,et al.  RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information , 2018, EMNLP.

[37]  Jieyu Zhao,et al.  Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods , 2018, NAACL.

[38]  Luke S. Zettlemoyer,et al.  Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations , 2011, ACL.

[39]  Gerhard Weikum,et al.  Neural Relation Extraction for Knowledge Base Enrichment , 2019, ACL.

[40]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[41]  Mounia Lalmas,et al.  First Women, Second Sex: Gender Bias in Wikipedia , 2015, HT.

[42]  Zeyu Li,et al.  Learning Gender-Neutral Word Embeddings , 2018, EMNLP.

[43]  David García,et al.  It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopedia , 2015, ICWSM.

[44]  Ming Gao,et al.  Improving Neural Relation Extraction with Implicit Mutual Relations , 2019, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[45]  Li Zhao,et al.  Reinforcement Learning for Relation Classification From Noisy Data , 2018, AAAI.

[46]  Mai ElSherief,et al.  Mitigating Gender Bias in Natural Language Processing: Literature Review , 2019, ACL.

[47]  Alexandra Chouldechova,et al.  What’s in a Name? Reducing Bias in Bios without Access to Protected Attributes , 2019, NAACL.

[48]  Alexandra Chouldechova,et al.  Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting , 2019, FAT.

[49]  Lucy Vasserman,et al.  Measuring and Mitigating Unintended Bias in Text Classification , 2018, AIES.

[50]  Xin Jiang,et al.  Neural Generative Question Answering , 2015, IJCAI.

[51]  Nanda Kambhatla,et al.  Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction , 2004, ACL.

[52]  Huang Xun,et al.  A Review of Relation Extraction , 2013 .

[53]  Xiao Lin,et al.  Building Knowledge Base through Deep Learning Relation Extraction and Wikidata , 2019, AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering.

[54]  Christopher D. Manning,et al.  Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling , 2005, ACL.

[55]  R. Shprintzen,et al.  What's in a name? , 1990, The Cleft palate journal.

[56]  Andrew McCallum,et al.  Relation Extraction with Matrix Factorization and Universal Schemas , 2013, NAACL.

[57]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[58]  Zhiyuan Liu,et al.  Neural Relation Extraction with Selective Attention over Instances , 2016, ACL.

[59]  Shikha Bordia,et al.  Identifying and Reducing Gender Bias in Word-Level Language Models , 2019, NAACL.

[60]  Luis Gravano,et al.  Snowball: extracting relations from large plain-text collections , 2000, DL '00.