D-Index & Metrics Best Publications

D-Index & Metrics

Discipline name D-index D-index (Discipline H-index) only includes papers and citation values for an examined discipline in contrast to General H-index which accounts for publications across all disciplines. Citations Publications World Ranking National Ranking
Computer Science D-index 35 Citations 11,719 107 World Ranking 6008 National Ranking 2920

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

His main research concerns Artificial intelligence, Natural language processing, Paraphrase, Sentence and Machine learning. Artificial neural network, Deep learning, Phrase and Bigram are the subjects of his Artificial intelligence studies. He has researched Natural language processing in several fields, including Annotation, Part-of-speech tagging, Word and Database.

His study in Paraphrase is interdisciplinary in nature, drawing from both Similarity, SemEval, Parametric statistics and Leverage. Kevin Gimpel usually deals with Sentence and limits it to topics linked to Convolutional neural network and Embedding, Speech recognition and Similarity. Kevin Gimpel regularly links together related areas like Natural language in his Machine learning studies.

His most cited work include:

  • ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (1030 citations)
  • Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments (812 citations)
  • Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters (599 citations)

What are the main themes of his work throughout his whole career to date?

Kevin Gimpel spends much of his time researching Artificial intelligence, Natural language processing, Machine learning, Sentence and Artificial neural network. As part of one scientific family, Kevin Gimpel deals mainly with the area of Artificial intelligence, narrowing it down to issues related to the Context, and often Focus. His biological study deals with issues like Similarity, which deal with fields such as Semantic similarity.

The study incorporates disciplines such as Language model and Inference in addition to Machine learning. His Language model research focuses on Transformer and how it relates to Natural language. His work carried out in the field of Sentence brings together such families of science as Semantics, Variety and Feature.

He most often published in these fields:

  • Artificial intelligence (79.37%)
  • Natural language processing (50.62%)
  • Machine learning (25.63%)

What were the highlights of his more recent work (between 2019-2021)?

  • Artificial intelligence (79.37%)
  • Natural language processing (50.62%)
  • Machine learning (25.63%)

In recent papers he was focusing on the following fields of study:

Kevin Gimpel mostly deals with Artificial intelligence, Natural language processing, Machine learning, Inference and Artificial neural network. His Parsing, Machine translation, Natural language inference, Representation and Coreference study are his primary interests in Artificial intelligence. Kevin Gimpel does research in Natural language processing, focusing on Sentence specifically.

His Sentence research is multidisciplinary, relying on both Probabilistic logic, Word, Statistical model and Operator. His study in Feature learning and Transformer is carried out as part of his Machine learning studies. He has included themes like Language model, Variety, Energy, Similarity and Sequence labeling in his Inference study.

Between 2019 and 2021, his most popular works were:

  • ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (1030 citations)
  • ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation (11 citations)
  • Improving Joint Training of Inference Networks and Structured Prediction Energy Networks. (6 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Machine learning
  • Statistics

Artificial intelligence, Machine learning, Inference, Machine translation and Energy are his primary areas of study. His research on Artificial intelligence frequently connects to adjacent areas such as Natural language processing. His Natural language processing research incorporates themes from Margin and Model selection.

His study looks at the relationship between Inference and fields such as Sequence labeling, as well as how they intersect with chemical problems. His Machine translation research includes themes of Energy based and Autoregressive model. His Feature learning study integrates concerns from other disciplines, such as Deep learning, Transformer and Self supervised learning.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Zhenzhong Lan;Mingda Chen;Sebastian Goodman;Kevin Gimpel.
international conference on learning representations (2020)

1959 Citations

Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments

Kevin Gimpel;Nathan Schneider;Brendan O'Connor;Dipanjan Das.
meeting of the association for computational linguistics (2011)

1213 Citations

Gaussian Error Linear Units (GELUs)

Dan Hendrycks;Kevin Gimpel.
arXiv: Learning (2016)

952 Citations

Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters

Olutobi Owoputi;Brendan O'Connor;Chris Dyer;Kevin Gimpel.
north american chapter of the association for computational linguistics (2013)

851 Citations

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

Dan Hendrycks;Kevin Gimpel.
international conference on learning representations (2016)

798 Citations

Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units

Dan Hendrycks;Kevin Gimpel.
arXiv: Learning (2016)

713 Citations

Towards Universal Paraphrastic Sentence Embeddings

John Wieting;Mohit Bansal;Kevin Gimpel;Karen Livescu.
international conference on learning representations (2016)

382 Citations

Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

Hua He;Kevin Gimpel;Jimmy Lin.
empirical methods in natural language processing (2015)

368 Citations

Tailoring Continuous Word Representations for Dependency Parsing

Mohit Bansal;Kevin Gimpel;Karen Livescu.
meeting of the association for computational linguistics (2014)

343 Citations

Movie Reviews and Revenues: An Experiment in Text Regression

Mahesh Joshi;Dipanjan Das;Kevin Gimpel;Noah A. Smith.
north american chapter of the association for computational linguistics (2010)

267 Citations

Best Scientists Citing Kevin Gimpel

Noah A. Smith

Noah A. Smith

University of Washington

Publications: 61

Ivan Vulić

Ivan Vulić

University of Cambridge

Publications: 43

Maosong Sun

Maosong Sun

Tsinghua University

Publications: 43

Chris Dyer

Chris Dyer

Google (United States)

Publications: 42

Hai Zhao

Hai Zhao

Shanghai Jiao Tong University

Publications: 40

Qun Liu

Qun Liu

Huawei Technologies (China)

Publications: 36

Hinrich Schütze

Hinrich Schütze

Ludwig-Maximilians-Universität München

Publications: 35

Caiming Xiong

Caiming Xiong

Salesforce (United States)

Publications: 33

Mohit Bansal

Mohit Bansal

University of North Carolina at Chapel Hill

Publications: 33

Yejin Choi

Yejin Choi

Allen Institute for Artificial Intelligence

Publications: 32

Xiang Ren

Xiang Ren

University of Southern California

Publications: 31

Jiwei Li

Jiwei Li

Zhejiang University

Publications: 28

Ming Zhou

Ming Zhou

Sinovation Ventures

Publications: 28

Wanxiang Che

Wanxiang Che

Harbin Institute of Technology

Publications: 27

Graham Neubig

Graham Neubig

Carnegie Mellon University

Publications: 27

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking d-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us
Something went wrong. Please try again later.