---
title: "Andrew Y. Ng — author profile and papers"
description: "Andrew Y. Ng: 9 papers on Elamur Research (2003–2020), h-index 14 — affiliations, topics, co-authors and who cites them in our library."
canonical: "https://research.elamur.ai/free/en/authors/andrew-y-ng/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/andrew-y-ng/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Andrew Y. Ng

# Andrew Y. Ng

Andrew Y. Ng works on machine learning and its uses in language, speech and medicine. The papers in this library range from probabilistic models of document collections to neural networks that learn word and phrase meanings, sentiment and the content of images, and further to end-to-end speech recognition and the labelling of clinical reports. A shared concern is learning useful representations from data instead of building them by hand.

The most cited paper here is [Latent Dirichlet Allocation](https://md.research.elamur.ai/free/en/papers/blei-2003-latent-dirichlet-allocation/) (2003), written with David M. Blei, which treats each document as a mixture of latent topics within a full generative model, so that new documents can be scored without the parameter growth of earlier approaches. [Learning Word Vectors for Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/maas-2011-learning-word-vectors-sentiment-analysis/) (2011) adds a sentiment signal to unsupervised word vectors so that words of opposite polarity no longer sit close together. Papers with Richard Socher build meanings of phrases from their parts with recursive neural networks, giving each word both a vector and a matrix (2012) or training recursive autoencoders on sentiment (2011).

The later entries apply such models to other signals. [Deep Speech](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/) (2014) replaces a chain of hand-tuned speech components with one recurrent network that maps spectrograms to characters. [Combining Automatic Labelers and Expert Annotations](https://md.research.elamur.ai/free/en/papers/smit-2020-combining-automatic-labelers-expert-annotations/) (2020) trains a BERT model on reports labelled by rules and then on expert annotations, to label chest x-ray reports more accurately.

Ng's main affiliation is Stanford University, with shorter links to Carnegie Mellon University and Microsoft. Frequent co-authors on this site are [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) and [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/), with [David M. Blei](https://md.research.elamur.ai/free/en/authors/david-m-blei/) on the topic model paper. The most common topic is [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/).

9 papers on this site · 2003–2020

Andrew Y. Ng has 9 papers on this site, in 2003–2020, most of them on [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/), [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/); 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/), [Eric Huang](https://md.research.elamur.ai/free/en/authors/eric-huang/).

[OpenAlex](https://openalex.org/A5023259221) · [ORCID](https://orcid.org/0000-0002-0016-2275) · [**h-index 14**](https://openalex.org/authors/A5023259221) · [16 works](https://openalex.org/works?filter=author.id:A5023259221) · [3 153 citations](https://openalex.org/works?filter=author.id:A5023259221&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[9 works on this site](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/#papers) · [5 030 citations in our library](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/cited-by/) · 2 more works in our library

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=Andrew+Y.+Ng) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Andrew+Y.+Ng) · [dblp](https://dblp.org/search?q=Andrew+Y.+Ng) · [ACL Anthology](https://aclanthology.org/search/?q=Andrew+Y.+Ng)

## Affiliations

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) · Stanford, United States —2005–2026 on 83 papers
- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · Pittsburgh, United States —2013–2018 on 2 papers
- [Microsoft (United States)](https://md.research.elamur.ai/free/en/companies/microsoft/) · Redmond, United States —2002 on 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed.

## Topics

[Sentiment & emotion 2](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Speech & spoken language 1](https://md.research.elamur.ai/free/en/topics/speech/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/)

## Works by year

### 2020s

[**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/smit-2020-combining-automatic-labelers-expert-annotations/)

### 2010s

[**2014** 2 papers](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/year/2014/) · [**2012** 2 papers](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/year/2012/) · [**2011** 2 papers](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/year/2011/)

### 2000s

[**2008** 1 paper](https://md.research.elamur.ai/free/en/papers/snow-2008-cheap-fast-but-is-it/) · [**2003** 1 paper](https://md.research.elamur.ai/free/en/papers/blei-2003-latent-dirichlet-allocation/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Latent Dirichlet Allocation](https://md.research.elamur.ai/free/en/papers/blei-2003-latent-dirichlet-allocation/)** *(2003 · 28 297 citations)* The paper addresses how to obtain compact, statistically meaningful representations of documents and other collections of discrete data.
2. **[Learning Word Vectors for Sentiment Analysis](https://md.research.elamur.ai/free/en/papers/maas-2011-learning-word-vectors-sentiment-analysis/)** *(2011 · 4 272 citations)* Word vectors learned without supervision capture topical similarity well but often miss polarity. In such vectors, "wonderful" and "terrible" can end up close together because they appear in similar contexts. Maas et al. address this with a model that has two parts. The first is an unsupervised probabilistic document…
3. **[Deep Speech: Scaling up end-to-end speech recognition](https://md.research.elamur.ai/free/en/papers/hannun-2014-deep-speech-scaling-up-end/)** *(2014 · 1 575 citations)* Conventional speech recognizers chain together many hand-tuned components, including engineered features, acoustic models, HMMs and phoneme dictionaries.
4. **[Semantic Compositionality through Recursive Matrix-Vector Spaces](https://md.research.elamur.ai/free/en/papers/socher-2012-semantic-compositionality-through-recursive-matrix/)** *(2012 · 1 559 citations)* Word vector models capture lexical meaning well, but they cannot represent how words combine into the meaning of longer phrases.
5. **[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.
6. **[Improving Word Representations via Global Context and Multiple Word Prototypes](https://md.research.elamur.ai/free/en/papers/huang-2012-improving-word-representations-global-context/)** *(2012 · 1 349 citations)* Most word embedding models learn one vector per word from a narrow window of neighbouring words. This ignores two things: words often have several unrelated or related senses, and the surrounding document carries topical cues. Huang et al. address both. They extend the Collobert and Weston ranking-loss language model…
7. **[Grounded Compositional Semantics for Finding and Describing Images with Sentences](https://md.research.elamur.ai/free/en/papers/socher-2014-grounded-compositional-semantics-finding-describing/)** *(2014 · 909 citations)* Earlier Recursive Neural Networks (RNNs) produced sentence vectors that captured syntax well but did not reflect what a sentence shows visually.
8. **[Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks](https://md.research.elamur.ai/free/en/papers/snow-2008-cheap-fast-but-is-it/)** *(2008 · 390 citations)* Expert linguistic annotation is slow and costly. This paper asks whether crowds of paid non-experts on Amazon Mechanical Turk (AMT) can stand in for specialists. The authors picked five tasks for which expert gold labels already existed: judging emotion in text (affect recognition), rating how similar pairs of words…
9. **[Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT](https://md.research.elamur.ai/free/en/papers/smit-2020-combining-automatic-labelers-expert-annotations/)** *(2020 · 334 citations)* Large chest x-ray datasets get their training labels from free-text radiology reports. Older labelers rely on hand-written rules, which miss much of the nuance in clinical language. Newer Transformer labelers instead need many costly expert annotations. The authors combine the two sources. They start from a…

## Also in our library

2 more works of theirs are in our library without a page here yet; they will appear as we publish them.

## Co-authors here

12 of 20 co-authors with a page, the most papers together first.

- [Christopher D. Manning](https://md.research.elamur.ai/free/en/authors/christopher-d-manning/) ×4
- [Richard Socher](https://md.research.elamur.ai/free/en/authors/richard-socher/) ×4
- [Eric Huang](https://md.research.elamur.ai/free/en/authors/eric-huang/) ×2
- [Adam Coates](https://md.research.elamur.ai/free/en/authors/adam-coates/)
- [Andrej Karpathy](https://md.research.elamur.ai/free/en/authors/andrej-karpathy/)
- [Anuj Pareek](https://md.research.elamur.ai/free/en/authors/anuj-pareek/)
- [Brendan O'Connor](https://md.research.elamur.ai/free/en/authors/brendan-o-connor/)
- [Bryan Catanzaro](https://md.research.elamur.ai/free/en/authors/bryan-catanzaro/)
- [Carl Case](https://md.research.elamur.ai/free/en/authors/carl-case/)
- [Christopher Potts](https://md.research.elamur.ai/free/en/authors/christopher-potts/)
- [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/)
- [David M. Blei](https://md.research.elamur.ai/free/en/authors/david-m-blei/)

## Cited by

Papers of our library cite their works 5 030 times (of the 140 884 papers whose bibliographies we read); [306 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/andrew-y-ng/cited-by/).