Recent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction. While much attention has been dedicated towards improvements in accuracy, there have been no attempts in the literature to evaluate social biases exhibited in NRE systems. In this paper, we create WikiGenderBias, a distantly supervised dataset composed of over 45,000 sentences including a 10% human annotated test set for the purpose of analyzing gender bias in relation extraction systems. We find that when extracting spouse-of and hypernym (i.e., occupation) relations, an NRE system performs differently when the gender of the target entity is different. However, such disparity does not appear when extracting relations such as birthDate or birthPlace. We also analyze how existing bias mitigation techniques, such as name anonymization, word embedding debiasing, and data augmentation affect the NRE system in terms of maintaining the test performance and reducing biases. Unfortunately, due to NRE models rely heavily on surface level cues, we find that existing bias mitigation approaches have a negative effect on NRE. Our analysis lays groundwork for future quantifying and mitigating bias in NRE.
more »
« less
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.
more »
« less
- Award ID(s):
- 1821415
- NSF-PAR ID:
- 10194807
- Date Published:
- Journal Name:
- Association for Computational Linguistics (ACL 2019)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The prevalent commercial deployment of automated facial analysis systems such as face recognition as a robust authentication method has increasingly fueled scientific attention. Current machine learning algorithms allow for a relatively reliable detection, recognition, and categorization of face images comprised of age, race, and gender. Algorithms with such biased data are bound to produce skewed results. It leads to a significant decrease in the performance of state-of-the-art models when applied to images of gender or ethnicity groups. In this paper, we study the gender bias in facial recognition with gender balanced and imbalanced training sets using five traditional machine learning algorithms. We aim to report the machine learning classifiers which are inclined towards gender bias and the ones which mitigate it. Miss rates metric is effective in finding out potential bias in predictions. Our study utilizes miss rates metric along with a standard metric such as accuracy, precision or recall to evaluate possible gender bias effectively.more » « less
-
Emphasizing socio-political context in undergraduate engineering courses is a complex challenge for accredited American engineering programs as they strive to pivot towards a more equitable future. Teaching engineering problem solving by isolating the technical perspective is the dominant culture, and change has been slow and insufficient. Looking at the complex human circumstances in which engineered systems are situated has significant, and sometimes life saving, benefits. On the contrary, the common de-contextualized approach to teaching engineering has been shown to have significant impacts on how students behave as future engineers. Furthermore, eurocentric teaching practices have been documented as a contributor to the lack of gender and ethinic diversity in engineering. Re-contextualizing civil engineering courses has shown to increase students' motivation, sense of social responsibility, and agency. The ASCE Code of Ethics states that “Engineers … first and foremost, protect the health, safety, and welfare of the public,” a notion that was first added to the code in 1977. In recent years, some civil and environmental engineering (CEE) faculty members and programs have responded to this ethical imperative by re-contextualizing civil engineering education in relation to the communities (“the public”) the civil engineer is ethically obligated to protect and serve. To determine the extent of these efforts to re-introduce socio-technical context in CEE curricula, we are conducting a systematic review of the published literature. The objectives of this research are to document, synthesize, and amplify the work of these scholars and to encourage the community of CEE faculty to re-contextualize the knowledge and skills taught in the CEE curriculum. This paper describes the methodology, including search terms and sources examined, reports the preliminary results of the review, and synthesizes the preliminary findings. Future work will propose strategies and structures that could be adapted and employed by civil engineering faculty throughout the U.S. to 1) engage and retain students from groups that historically have been excluded from CEE and 2) better educate CEE students to engineer a more equitable and just future.more » « less
-
Emphasizing socio-political context in undergraduate engineering courses is a complex challenge for accredited American engineering programs as they strive to pivot towards a more equitable future. Teaching engineering problem solving by isolating the technical perspective is the dominant culture, and change has been slow and insufficient. Looking at the complex human circumstances in which engineered systems are situated has significant, and sometimes life saving, benefits. On the contrary, the common de-contextualized approach to teaching engineering has been shown to have significant impacts on how students behave as future engineers. Furthermore, eurocentric teaching practices have been documented as a contributor to the lack of gender and ethinic diversity in engineering. Re-contextualizing civil engineering courses has shown to increase students' motivation, sense of social responsibility, and agency. The ASCE Code of Ethics states that “Engineers … first and foremost, protect the health, safety, and welfare of the public,” a notion that was first added to the code in 1977. In recent years, some civil and environmental engineering (CEE) faculty members and programs have responded to this ethical imperative by re-contextualizing civil engineering education in relation to the communities (“the public”) the civil engineer is ethically obligated to protect and serve. To determine the extent of these efforts to re-introduce socio-technical context in CEE curricula, we are conducting a systematic review of the published literature. The objectives of this research are to document, synthesize, and amplify the work of these scholars and to encourage the community of CEE faculty to re-contextualize the knowledge and skills taught in the CEE curriculum. This paper describes the methodology, including search terms and sources examined, reports the preliminary results of the review, and synthesizes the preliminary findings. Future work will propose strategies and structures that could be adapted and employed by civil engineering faculty throughout the U.S. to 1) engage and retain students from groups that historically have been excluded from CEE and 2) better educate CEE students to engineer a more equitable and just future.more » « less
-
Emphasizing socio-political context in undergraduate engineering courses is a complex challenge for accredited American engineering programs as they strive to pivot towards a more equitable future. Teaching engineering problem solving by isolating the technical perspective is the dominant culture, and change has been slow and insufficient. Looking at the complex human circumstances in which engineered systems are situated has significant, and sometimes life saving, benefits. On the contrary, the common de-contextualized approach to teaching engineering has been shown to have significant impacts on how students behave as future engineers. Furthermore, eurocentric teaching practices have been documented as a contributor to the lack of gender and ethinic diversity in engineering. Re-contextualizing civil engineering courses has shown to increase students' motivation, sense of social responsibility, and agency. The ASCE Code of Ethics states that “Engineers … first and foremost, protect the health, safety, and welfare of the public,” a notion that was first added to the code in 1977. In recent years, some civil and environmental engineering (CEE) faculty members and programs have responded to this ethical imperative by re-contextualizing civil engineering education in relation to the communities (“the public”) the civil engineer is ethically obligated to protect and serve. To determine the extent of these efforts to re-introduce socio-technical context in CEE curricula, we are conducting a systematic review of the published literature. The objectives of this research are to document, synthesize, and amplify the work of these scholars and to encourage the community of CEE faculty to re-contextualize the knowledge and skills taught in the CEE curriculum. This paper describes the methodology, including search terms and sources examined, reports the preliminary results of the review, and synthesizes the preliminary findings. Future work will propose strategies and structures that could be adapted and employed by civil engineering faculty throughout the U.S. to 1) engage and retain students from groups that historically have been excluded from CEE and 2) better educate CEE students to engineer a more equitable and just future.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
