--- title: "Yingyu Liang — author profile and papers" description: "Yingyu Liang, University of Wisconsin–Madison: 2 papers on Elamur Research (2016–2018), h-index 33 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/yingyu-liang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yingyu-liang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yingyu Liang # Yingyu Liang Yingyu Liang's papers here study the theory behind word embeddings: why vectors learned from word co-occurrence statistics behave as they do. The work asks what geometric structure such vectors carry, why low-dimensional inner products approximate co-occurrence measures, and how a single vector can stand for a word with many meanings. The method is to build a probabilistic generative model of text and derive from it the properties of embeddings such as word2vec and GloVe. This places the papers within [lexical semantics and word embeddings](https://md.research.elamur.ai/free/en/topics/lexical-semantics/) and [word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/). The most cited paper, [A Latent Variable Model Approach to PMI-based Word Embeddings](https://md.research.elamur.ai/free/en/papers/arora-2016-latent-variable-model-approach-pmi/) (2016), proposes that text is produced by a slowly drifting latent discourse vector. The chance of any given word appearing rises exponentially with how closely its own vector aligns with the current discourse. Under an assumption that word vectors are spread evenly in space, the model accounts for two observations. The pointwise mutual information matrix is well fit by low-dimensional vectors, and analogies can be solved by simple vector arithmetic. The follow-up, [Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://md.research.elamur.ai/free/en/papers/arora-2018-linear-algebraic-structure-word-senses/) (2018), argues that the vector of an ambiguous word is a weighted nonnegative combination of vectors for its separate senses. It supports this with a Gaussian variant of the random-walk model, in which a word's embedding is a linear transformation of averaged context embeddings. The later of these papers moves from explaining embeddings in general to the problem of polysemy, asking how the several meanings of a word sit inside its single vector. Liang's current institutions are the [University of Wisconsin–Madison](https://md.research.elamur.ai/free/en/universities/university-of-wisconsin-madison/) and the [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/), and earlier bylines include [Princeton University](https://md.research.elamur.ai/free/en/universities/princeton-university/). Co-authors on these papers include [Sanjeev Arora](https://md.research.elamur.ai/free/en/authors/sanjeev-arora/), [Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/), [Tengyu Ma](https://md.research.elamur.ai/free/en/authors/tengyu-ma/) and [Andrej Risteski](https://md.research.elamur.ai/free/en/authors/andrej-risteski/). Yingyu Liang has 2 papers in our library, in 2016–2018, most of them on [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/), [Lexical semantics & word embeddings](https://md.research.elamur.ai/free/en/topics/lexical-semantics/); often with [Andrej Risteski](https://md.research.elamur.ai/free/en/authors/andrej-risteski/), [Sanjeev Arora](https://md.research.elamur.ai/free/en/authors/sanjeev-arora/), [Tengyu Ma](https://md.research.elamur.ai/free/en/authors/tengyu-ma/). 2 papers in our library · 2016–2018 [OpenAlex](https://openalex.org/A5035905957) · [ORCID](https://orcid.org/0000-0002-3644-774X) · [**h-index 33**](https://openalex.org/authors/A5035905957) · [150 works](https://openalex.org/works?filter=author.id:A5035905957) · [4,599 citations](https://openalex.org/works?filter=author.id:A5035905957&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/yingyu-liang/#papers) · [🔗 160 citations in our library](https://md.research.elamur.ai/free/en/authors/yingyu-liang/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #2678](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2678) 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=Yingyu+Liang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yingyu+Liang) · [dblp](https://dblp.org/search?q=Yingyu+Liang) · [ACL Anthology](https://aclanthology.org/search/?q=Yingyu+Liang) ## Affiliations [🎓**University of Wisconsin–Madison** Madison · United States 2017–2026 · 49 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-wisconsin-madison/) · [🎓**University of Hong Kong** Pok Fu Lam · Hong Kong 2024–2026 · 12 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) · [🎓**Princeton University** Princeton · United States 2011–2018 · 23 papers](https://md.research.elamur.ai/free/en/universities/princeton-university/) · [🎓**Georgia Institute of Technology** Atlanta · United States 2012–2014 · 7 papers](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) · [🎓**Xi'an Technological University** Xi'an · China 2020–2022 · 5 papers](https://ror.org/01t8prc81) · [🎓**China University of Mining and Technology - Beijing** Beijing 2022–2025 · 3 papers](https://ror.org/003ncxf91) · [🎓**UNSW Sydney** Sydney · Australia 2024–2025 · 3 papers](https://md.research.elamur.ai/free/en/universities/unsw-sydney/) · [🎓**Tsinghua University** Beijing · China 2009–2012 · 3 papers](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [🎓**Guangdong Pharmaceutical University** Guangzhou · China 2025 · 2 papers](https://ror.org/02vg7mz57) · [🎓**University of California, Berkeley** Berkeley · United States 2024–2025 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 more institutions on single bylines are not listed. ## Topics [Word sense disambiguation (1)](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) · [Lexical semantics & word embeddings (1)](https://md.research.elamur.ai/free/en/topics/lexical-semantics/) ## Works by year ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/arora-2018-linear-algebraic-structure-word-senses/) · [**2016** 1 paper](https://md.research.elamur.ai/free/en/papers/arora-2016-latent-variable-model-approach-pmi/) ## Papers The most cited first (OpenAlex and our library). 1. **[A Latent Variable Model Approach to PMI-based Word Embeddings](https://md.research.elamur.ai/free/en/papers/arora-2016-latent-variable-model-approach-pmi/)** *(2016 · 365 citations)* Embeddings derived from co-occurrence statistics, such as PMI matrices, word2vec and GloVe, work well in practice. 2. **[Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://md.research.elamur.ai/free/en/papers/arora-2018-linear-algebraic-structure-word-senses/)** *(2018 · 247 citations)* The paper asks what a single word vector encodes when the word has several meanings. The authors argue that standard embeddings such as word2vec and GloVe store a polysemous word as a weighted, nonnegative sum of vectors for its individual senses. They support this "Linearity Assertion" with theory. They modify the… ## 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 4 co-authors with a page, the most papers together first. - [Andrej Risteski](https://md.research.elamur.ai/free/en/authors/andrej-risteski/) ×2 - [Sanjeev Arora](https://md.research.elamur.ai/free/en/authors/sanjeev-arora/) ×2 - [Tengyu Ma](https://md.research.elamur.ai/free/en/authors/tengyu-ma/) ×2 - [Yuanzhi Li](https://md.research.elamur.ai/free/en/authors/yuanzhi-li/) ×2 ## Cited by Papers of our library cite their works 160 times (of the 140,884 papers whose bibliographies we read); [12 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/yingyu-liang/cited-by/).