Elamur Research⌕
☰
home / authors / Cong Yu

Cong Yu

Cong Yu has 2 papers in our library, in 2020–2021, most of them on Evaluation & benchmarks, Tokenization & segmentation; often with Dara Bahri, Dian Yu, Donald Metzler.

2 papers in our library · 2020–2021

OpenAlex · ORCID · h-index 48 · 218 works · 8,185 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 300 citations in our library · 1 more in our library without a page yet · ⭐ Paper Star rank #3168

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Chengdu Agricultural CollegeChengdu · China2026 · 1 papercurrent🏢GoogleMountain View · United States2010–2022 · 66 papers🎓University of MichiganAnn Arbor · United States2002–2007 · 20 papers🎓Morgan State UniversityBaltimore · United States2009–2024 · 18 papers🏢YahooSunnyvale · United States2008–2010 · 17 papers🎓University of Hong KongPok Fu Lam · Hong Kong2015–2024 · 12 papers🎓Qingdao University of TechnologyQingdao · China2013–2025 · 11 papers🎓Hefei University of TechnologyHefei · China2020–2025 · 9 papers🎓Nanjing University of Posts and TelecommunicationsNanjing · China2019 · 5 papers🎓Towson UniversityTowson · United States2006–2019 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 24 more institutions on single bylines are not listed.

 Topics

 Evaluation & benchmarks (1) Tokenization & segmentation (1)

 Works by year

2020s

20211 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. CLUE: A Chinese Language Understanding Evaluation Benchmark (2020 · 242 citations)
    Shared benchmarks such as GLUE and SuperGLUE have driven progress in English NLU, but Chinese had no comparable standard.
  2. Charformer: Fast Character Transformers via Gradient-based Subword Tokenization (2021 · 179 citations)
    Most NLP models rely on a subword tokenizer that is fixed before training. This makes them fragile to rare words, typos and noisy text. It also breaks low-resource languages into many fragments and makes adaptation to new domains harder. Feeding raw characters to a Transformer avoids these issues, but the long…

Also in our library

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

 Co-authors here

12 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 300 times (of the 140,884 papers whose bibliographies we read); 40 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/cong-yu/