--- title: "Jieyu Zhao — author profile and papers" description: "Jieyu Zhao, University of Southern California: 5 papers on Elamur Research (2017–2019), h-index 20 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/jieyu-zhao/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jieyu-zhao/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jieyu Zhao # Jieyu Zhao Jieyu Zhao studies gender bias in natural language processing and in vision tasks grounded in language. The papers here, published between 2017 and 2019, ask how stereotypes in training corpora reach learned models, whether models exaggerate those skews, and how such effects can be measured and reduced. The methods include purpose-built challenge sets, bias scores that compare predictions with training statistics, constraints applied at inference time, and changes to how embeddings are trained. Coreference resolution serves as a recurring test case. The most cited work is [Gender Bias in Coreference Resolution](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/) (2018). It introduced WinoBias, a Winograd-style set of sentences about people named by occupation, each written with both a male and a female pronoun so that gender should never decide the answer. [Men Also Like Shopping](https://md.research.elamur.ai/free/en/papers/zhao-2017-men-also-like-shopping-reducing/) (2017) showed that structured predictors for visual semantic role labeling and multilabel object classification widen the gender skews already present in web-sourced images, and it curbed that amplification with corpus-level constraints. [Learning Gender-Neutral Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2018-learning-gender-neutral-word-embeddings/) (2018) proposed GN-GloVe, which adds terms to the GloVe objective so that gender information is handled during training rather than removed afterwards. The newest papers here, from 2019, extend these questions beyond static vectors. [Gender Bias in Contextualized Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/) examines ELMo through counts of gendered pronouns in its corpus, PCA on gender-swapped sentences and an occupation probe. It then tests an ELMo-based coreference system on WinoBias. A co-authored literature review on mitigating gender bias in NLP sorts known problems in translation, image description, speech recognition and other applications. It groups them using a split between allocation harms and representation harms. Zhao is at the [University of Southern California](https://md.research.elamur.ai/free/en/universities/university-of-southern-california/). Earlier affiliations include the [University of California, Los Angeles](https://md.research.elamur.ai/free/en/universities/university-of-california-los-angeles/) and the [University of Maryland, College Park](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/). Frequent co-authors include [Kai-Wei Chang](https://md.research.elamur.ai/free/en/authors/kai-wei-chang/), Mark Yatskar, Tianlu Wang and [Vicente Ordonez](https://md.research.elamur.ai/free/en/authors/vicente-ordonez/). Most of the work falls under [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/). Jieyu Zhao has 5 papers in our library, in 2017–2019, most of them on [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/); often with [Kai-Wei Chang](https://md.research.elamur.ai/free/en/authors/kai-wei-chang/), [Mark Yatskar](https://md.research.elamur.ai/free/en/authors/mark-yatskar/), [Tianlu Wang](https://md.research.elamur.ai/free/en/authors/tianlu-wang/). 5 papers in our library · 2017–2019 [OpenAlex](https://openalex.org/A5066282713) · [ORCID](https://orcid.org/0000-0002-1013-557X) · [Wikidata](https://www.wikidata.org/wiki/Q90414610) · [**h-index 20**](https://openalex.org/authors/A5066282713) · [165 works](https://openalex.org/works?filter=author.id:A5066282713) · [4,368 citations](https://openalex.org/works?filter=author.id:A5066282713&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/jieyu-zhao/#papers) · [🔗 1,366 citations in our library](https://md.research.elamur.ai/free/en/authors/jieyu-zhao/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Star rank #648](https://md.research.elamur.ai/free/en/paper-stars/page/7/#star-648) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Jieyu+Zhao) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jieyu+Zhao) · [dblp](https://dblp.org/search?q=Jieyu+Zhao) · [ACL Anthology](https://aclanthology.org/search/?q=Jieyu+Zhao) ## Affiliations [🎓**University of Southern California** Los Angeles · United States 2023–2026 · 20 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-southern-california/) · [🎓**Ningbo University** Ningbo · China 2001–2025 · 82 papersEmployment since 2001](https://ror.org/03et85d35) · [🎓**University of California, Los Angeles** Los Angeles · United States 2018–2023 · 21 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-los-angeles/) · [🎓**University of Maryland, College Park** College Park · United States 2022–2024 · 6 papers](https://md.research.elamur.ai/free/en/universities/university-of-maryland-college-park/) · [🎓**Beihang University** Beijing · China 2014–2024 · 3 papers](https://md.research.elamur.ai/free/en/universities/beihang-university/) · [🎓**University of California, Santa Barbara** Santa Barbara · United States 2019–2020 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/) · [🎓**Ningbo University of Technology** Ningbo · China 2008–2019 · 2 papers](https://ror.org/037dym702) · [🔬**Dalle Molle Institute for Artificial Intelligence Research** Lugano · Switzerland 1997 · 2 papers](https://ror.org/013355g38) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 13 more institutions on single bylines are not listed. ## Topics [Bias, fairness & safety (4)](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Coreference resolution (1)](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) ## Works by year ### 2010s [**2019** 2 papers](https://md.research.elamur.ai/free/en/authors/jieyu-zhao/year/2019/) · [**2018** 2 papers](https://md.research.elamur.ai/free/en/authors/jieyu-zhao/year/2018/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/zhao-2017-men-also-like-shopping-reducing/) ## Papers The most cited first (OpenAlex and our library). 1. **[Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://md.research.elamur.ai/free/en/papers/zhao-2018-gender-bias-coreference-resolution-evaluation/)** *(2018 · 1,186 citations)* The paper asks whether coreference resolution systems rely on gender stereotypes about occupations. The authors build WinoBias, a Winograd-style challenge set of 3,160 sentences. Each sentence mentions two people by occupation, drawn from 40 jobs whose gender ratios come from US Department of Labor statistics. Every… 2. **[Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://md.research.elamur.ai/free/en/papers/zhao-2017-men-also-like-shopping-reducing/)** *(2017 · 1,030 citations)* Vision tasks grounded in language often use structured predictors that exploit correlations between labels. 3. **[Mitigating Gender Bias in Natural Language Processing: Literature Review](https://md.research.elamur.ai/free/en/papers/sun-2019-mitigating-gender-bias-natural-language/)** *(2019 · 716 citations)* This survey, presented at ACL 2019, examines how gender bias enters NLP systems and what has been tried to reduce it. 4. **[Learning Gender-Neutral Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2018-learning-gender-neutral-word-embeddings/)** *(2018 · 512 citations)* Word vectors trained on human-written text pick up gender stereotypes. Occupation words such as "programmer" or "doctor" drift toward one gender, and that bias can carry into systems like coreference resolvers or resume screeners. An earlier remedy by Bolukbasi et al. (2016), used here as the Hard-GloVe baseline… 5. **[Gender Bias in Contextualized Word Embeddings](https://md.research.elamur.ai/free/en/papers/zhao-2019-gender-bias-contextualized-word-embeddings/)** *(2019 · 503 citations)* The paper asks whether contextualized embeddings carry the same gender stereotypes already documented for static vectors such as GloVe, and whether that bias reaches downstream systems. ## Also in our library 4 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 9 co-authors with a page, the most papers together first. - [Kai-Wei Chang](https://md.research.elamur.ai/free/en/authors/kai-wei-chang/) ×5 - [Mark Yatskar](https://md.research.elamur.ai/free/en/authors/mark-yatskar/) ×3 - [Tianlu Wang](https://md.research.elamur.ai/free/en/authors/tianlu-wang/) ×3 - [Vicente Ordonez](https://md.research.elamur.ai/free/en/authors/vicente-ordonez/) ×3 - [Elizabeth Belding](https://md.research.elamur.ai/free/en/authors/elizabeth-belding/) - [Mai ElSherief](https://md.research.elamur.ai/free/en/authors/mai-elsherief/) - [Ryan Cotterell](https://md.research.elamur.ai/free/en/authors/ryan-cotterell/) - [Wei Wang](https://md.research.elamur.ai/free/en/authors/wei-wang/) - [William Yang Wang](https://md.research.elamur.ai/free/en/authors/william-yang-wang/) ## Cited by Papers of our library cite their works 1,366 times (of the 140,884 papers whose bibliographies we read); [114 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jieyu-zhao/cited-by/).