Picture for Seraphina Goldfarb-Tarrant

Seraphina Goldfarb-Tarrant

This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models

May 22, 2023
Seraphina Goldfarb-Tarrant, Eddie Ungless, Esma Balkir, Su Lin Blodgett

* Accepted to ACL Findings 2023

Access Paper or Ask Questions

Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis

May 22, 2023
Seraphina Goldfarb-Tarrant, Björn Ross, Adam Lopez

* 8 pages, preprint

Access Paper or Ask Questions

Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages

May 19, 2023
Seraphina Goldfarb-Tarrant, Adam Lopez, Roi Blanco, Diego Marcheggiani

* 5 pages, accepted to Findings of ACL 2023

Access Paper or Ask Questions

How Gender Debiasing Affects Internal Model Representations, and Why It Matters

Apr 14, 2022
Hadas Orgad, Seraphina Goldfarb-Tarrant, Yonatan Belinkov

Figure 1 for How Gender Debiasing Affects Internal Model Representations, and Why It Matters

Figure 2 for How Gender Debiasing Affects Internal Model Representations, and Why It Matters

Figure 3 for How Gender Debiasing Affects Internal Model Representations, and Why It Matters

Figure 4 for How Gender Debiasing Affects Internal Model Representations, and Why It Matters

* Accepted to NAACL 2022

Access Paper or Ask Questions

Intrinsic Bias Metrics Do Not Correlate with Application Bias

Jan 02, 2021
Seraphina Goldfarb-Tarrant, Rebecca Marchant, Ricardo Muñoz Sanchez, Mugdha Pandya, Adam Lopez

Figure 1 for Intrinsic Bias Metrics Do Not Correlate with Application Bias

Figure 2 for Intrinsic Bias Metrics Do Not Correlate with Application Bias

Figure 3 for Intrinsic Bias Metrics Do Not Correlate with Application Bias

Figure 4 for Intrinsic Bias Metrics Do Not Correlate with Application Bias

* early draft first preprint. 8 pages

Access Paper or Ask Questions

Content Planning for Neural Story Generation with Aristotelian Rescoring

Oct 09, 2020
Seraphina Goldfarb-Tarrant, Tuhin Chakrabarty, Ralph Weischedel, Nanyun Peng

Figure 1 for Content Planning for Neural Story Generation with Aristotelian Rescoring

Figure 2 for Content Planning for Neural Story Generation with Aristotelian Rescoring

Figure 3 for Content Planning for Neural Story Generation with Aristotelian Rescoring

Figure 4 for Content Planning for Neural Story Generation with Aristotelian Rescoring

* EMNLP 2020, 9 pages

Access Paper or Ask Questions

Scaling Systematic Literature Reviews with Machine Learning Pipelines

Oct 09, 2020
Seraphina Goldfarb-Tarrant, Alexander Robertson, Jasmina Lazic, Theodora Tsouloufi, Louise Donnison, Karen Smyth

Figure 1 for Scaling Systematic Literature Reviews with Machine Learning Pipelines

Figure 2 for Scaling Systematic Literature Reviews with Machine Learning Pipelines

Figure 3 for Scaling Systematic Literature Reviews with Machine Learning Pipelines

Figure 4 for Scaling Systematic Literature Reviews with Machine Learning Pipelines

* In EMNLP 2020 Scholarly Document Processing Workshop

Access Paper or Ask Questions

Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation

Apr 18, 2019
Seraphina Goldfarb-Tarrant, Haining Feng, Nanyun Peng

Figure 1 for Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation

Figure 2 for Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation

Figure 3 for Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation

Figure 4 for Plan, Write, and Revise: an Interactive System for Open-Domain Story Generation

* Accepted to NAACL 2019 Demo Track, 5 pages

Access Paper or Ask Questions