4701_yatskar-mark-squae.jpg

Mark Yatskar

Natural Language Processing (NLP) Gender Bias Amplification Language-structured Visual Perception Fairness In Machine Learning Multimodal Machine Learning
University of Pennsylvania Computer and Information Science

About

I am an Assistant Professor at University of Pennsylvania in the department of Computer and Information Science. I did my PhD at University of Washington co-advised by Luke Zettlemoyer and Ali Farhadi. I was a Young Investigator at the Allen Institute for Artificial Intelligence for several years working with their computer vision team, Prior. My work is interdisciplinary, spanning Natural Language Processing, Computer Vision, and Fairness in Machine Learning. I received a Best Paper Award at EMNLP for work on gender bias amplification (Wired article). My research broadly explores how language can be used to structure visual perception. I work on machine learning approaches that enable tight coupling between how people express themselves in language and how machine behavior is specified. A central thread in my research is trying to understand how machine learning systems inherit human bias.

Research Performance Summary

56
Total Papers
13889
Total Citations
29
H-Index
2010-2026
Active Research Span

First Recorded Paper

For the sake of simplicity: Unsupervised extraction of lexical simplifications from Wikipedia

Year: 2010

Citations: 228

Venue: Human Language Technologies: The 2010 Annual Conference of the North

Latest Recorded Paper

Purely Agentic Black-Box Optimization for Biological Design

Year: 2026

Citations: 0

Venue: arXiv preprint arXiv:2601.22382

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

2026
1
2025
9
2024
7
2023
8
2022
2
2021
5
2020
4
2019
6
2018
5
2017
4
2016
2

Publication Venues and Collaboration

Journal, Conference, and Book Publication Breakdown

Conference 32
Journal 2
Book 0

Top Coauthors

Yatskar Yang

Research Impact by Period

2025-2026

Period Stats
Papers 10
Citations 502
Avg. Citations / Paper 50.2
H-Index 5

2020-2024

Period Stats
Papers 26
Citations 2073
Avg. Citations / Paper 79.7
H-Index 16

2015-2019

Period Stats
Papers 17
Citations 11022
Avg. Citations / Paper 648.4
H-Index 14

2010-2014

Period Stats
Papers 3
Citations 292
Avg. Citations / Paper 97.3
H-Index 2

Contact and Professional Links

Contact Information

myatskar@cis.upenn.edu

Detected Research Keywords

Interpretable Design Text Iteratively Generated Concept Generated Concept Bottleneck Visualbert Simple Performant Simple Performant Baseline Performant Baseline Vision Baseline Vision Language Visual Semantic Role Semantic Role Labeling Caitlin Wittlif Carissa