--- title: "Jeffrey Pennington — author profile and papers" description: "Jeffrey Pennington: 2 papers on Elamur Research (2011–2014), h-index 20 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/jeffrey-pennington/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jeffrey-pennington/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jeffrey Pennington # Jeffrey Pennington Jeffrey Pennington works on learning vector representations of language. The papers here span 2011–2014 and return to one question: how continuous vectors for words and phrases can capture meaning, and how such vectors can be learned from text. One approach draws on co-occurrence statistics gathered across a whole corpus. Another composes word vectors step by step into representations of longer spans. The work also touches on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), using learned sentence representations to predict the feelings a text expresses. The most cited paper is [GloVe: Global Vectors for Word Representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/) (2014). It asks why word vectors tend to encode semantic relationships as linear offsets. Its answer is that ratios between co-occurrence probabilities, rather than the raw probabilities, are what carry meaning. On that basis it builds a weighted least-squares model trained on global counts. The model joins the strengths of matrix-factorization methods such as LSA with those of window-based methods such as skip-gram. Earlier, [Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/) (2011) learned sentence vectors by repeatedly merging neighbouring word vectors into a tree, with no parser or hand-built sentiment lexicon. It then predicted distributions over sentiment from those vectors. The newest paper here, GloVe, marks a shift from a compositional model built for one task toward general-purpose word vectors learned from corpus-wide statistics. Both papers date from Pennington's time at [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/). [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/) and [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) appear as co-authors on each, and [Andrew Y. Ng](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/) and [Eric Huang](https://md.research.elamur.ai/free/en/authors/eric-huang/) also contributed. Later bylines, from 2015 to 2022, list [Google](https://md.research.elamur.ai/free/en/companies/google/). Jeffrey Pennington has 2 papers in our library, in 2011–2014, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/); often with [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/), [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/), [Andrew Y. Ng](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/). 2 papers in our library · 2011–2014 [OpenAlex](https://openalex.org/A5010225522) · [**h-index 20**](https://openalex.org/authors/A5010225522) · [53 works](https://openalex.org/works?filter=author.id:A5010225522) · [35,859 citations](https://openalex.org/works?filter=author.id:A5010225522&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/jeffrey-pennington/#papers) · [6,358 citations in our library](https://md.research.elamur.ai/free/en/authors/jeffrey-pennington/cited-by/) · 1 more work in our library · [⭐ Paper Star rank #304](https://md.research.elamur.ai/free/en/paper-stars/page/4/#star-304) 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=Jeffrey+Pennington) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jeffrey+Pennington) · [dblp](https://dblp.org/search?q=Jeffrey+Pennington) · [ACL Anthology](https://aclanthology.org/search/?q=Jeffrey+Pennington) ## Affiliations [🏢**Google** Mountain View · United States 2015–2022 · 22 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Stanford University** Stanford · United States 2011–2014 · 2 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Sentiment & emotion 1](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) ## Works by year ### 2010s [**2014** 1 paper](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/) · [**2011** 1 paper](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/) ## Papers The most cited first (OpenAlex and our library). 1. **[GloVe: Global Vectors for Word Representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/)** *(2014 · 5,962 citations)* The paper explains why word vector representations capture semantic relationships as linear relations. The authors also propose a model that combines the strengths of two approaches. The first approach factorizes a global word co-occurrence matrix (like LSA). It makes good use of corpus statistics but performs poorly… 2. **[Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions](https://md.research.elamur.ai/free/en/papers/socher-2011-semi-supervised-recursive-autoencoders-predicting/)** *(2011 · 1,411 citations)* Most sentiment classifiers of the time relied on bag-of-words features, which ignore word order and composition. ## 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. - [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) ×2 - [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/) ×2 - [Andrew Y. Ng](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/) - [Eric Huang](https://md.research.elamur.ai/free/en/authors/eric-huang/) ## Cited by Papers of our library cite their works 6,358 times (of the 140,884 papers whose bibliographies we read); [557 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jeffrey-pennington/cited-by/).