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 64 Citations 24,243 173 World Ranking 1206 National Ranking 708

Research.com Recognitions

Awards & Achievements

2015 - Fellow of Alfred P. Sloan Foundation

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Programming language
  • Statistics

Percy Liang focuses on Artificial intelligence, Natural language processing, Question answering, Machine learning and Reading comprehension. His Artificial intelligence research is multidisciplinary, relying on both Domain, Simple and Set. He has researched Natural language processing in several fields, including Baseline, Utterance and Generative model.

His Question answering study deals with Dependency intersecting with Comprehension and Reading. His studies in Machine learning integrate themes in fields like End-to-end principle, Process and Inference. His Reading comprehension study combines topics from a wide range of disciplines, such as Context and F1 score.

His most cited work include:

  • SQuAD: 100,000+ Questions for Machine Comprehension of Text (2193 citations)
  • Semantic Parsing on Freebase from Question-Answer Pairs (1042 citations)
  • SQuAD: 100,000+ Questions for Machine Comprehension of Text (669 citations)

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

Percy Liang mainly investigates Artificial intelligence, Natural language processing, Machine learning, Parsing and Natural language. The various areas that Percy Liang examines in his Artificial intelligence study include Set and Pattern recognition. His research in Natural language processing intersects with topics in Domain, Context and Baseline.

His work deals with themes such as Principle of compositionality and Grammar, which intersect with Parsing. The concepts of his Training set study are interwoven with issues in Algorithm and Contrast. His Reading comprehension research extends to the thematically linked field of Question answering.

He most often published in these fields:

  • Artificial intelligence (49.82%)
  • Natural language processing (24.03%)
  • Machine learning (20.85%)

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

  • Artificial intelligence (49.82%)
  • Machine learning (20.85%)
  • Robustness (7.42%)

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

His primary scientific interests are in Artificial intelligence, Machine learning, Robustness, Spurious relationship and Algorithm. His Artificial intelligence research is multidisciplinary, incorporating elements of Domain, Graph and Natural language processing. His work carried out in the field of Natural language processing brings together such families of science as Representation and Baseline.

In his research on the topic of Machine learning, Transfer of learning is strongly related with Graph neural networks. His Algorithm study incorporates themes from MNIST database, Closing and Extrapolation. His studies deal with areas such as Contrast, Training set and Key as well as Question answering.

Between 2019 and 2021, his most popular works were:

  • Strategies for Pre-training Graph Neural Networks (79 citations)
  • Understanding and Mitigating the Tradeoff Between Robustness and Accuracy (29 citations)
  • Enabling Language Models to Fill in the Blanks. (22 citations)

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

  • Artificial intelligence
  • Programming language
  • Statistics

The scientist’s investigation covers issues in Artificial intelligence, Robustness, Training set, Machine learning and Spurious relationship. The study incorporates disciplines such as Domain, Graph and Natural language processing in addition to Artificial intelligence. He has included themes like Language model, Contrast, Question answering and Softmax function in his Domain study.

His research integrates issues of Representation and Baseline in his study of Natural language processing. Percy Liang usually deals with Robustness and limits it to topics linked to Artificial neural network and Algorithm, Linear programming and Solver. His Machine learning research is multidisciplinary, incorporating perspectives in Graph neural networks, Interpretation and Identification.

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

SQuAD: 100,000+ Questions for Machine Comprehension of Text

Pranav Rajpurkar;Jian Zhang;Konstantin Lopyrev;Percy Liang.
empirical methods in natural language processing (2016)

2193 Citations

Semantic Parsing on Freebase from Question-Answer Pairs

Jonathan Berant;Andrew Chou;Roy Frostig;Percy Liang.
empirical methods in natural language processing (2013)

1243 Citations

Understanding black-box predictions via influence functions

Pang Wei Koh;Percy Liang.
international conference on machine learning (2017)

734 Citations

Adversarial Examples for Evaluating Reading Comprehension Systems

Robin Jia;Percy Liang.
empirical methods in natural language processing (2017)

686 Citations

Know What You Don't Know: Unanswerable Questions for SQuAD

Pranav Rajpurkar;Robin Jia;Percy Liang.
meeting of the association for computational linguistics (2018)

653 Citations

Learning Dependency-Based Compositional Semantics

Percy Liang;Michael Jordan;Dan Klein.
meeting of the association for computational linguistics (2011)

542 Citations

Alignment by Agreement

Percy Liang;Ben Taskar;Dan Klein.
language and technology conference (2006)

536 Citations

Semantic Parsing via Paraphrasing

Jonathan Berant;Percy Liang.
meeting of the association for computational linguistics (2014)

500 Citations

Data Recombination for Neural Semantic Parsing

Robin Jia;Percy Liang.
meeting of the association for computational linguistics (2016)

428 Citations

Semi-Supervised Learning for Natural Language

Percy Liang.
(2005)

408 Citations

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

Contact us

Best Scientists Citing Percy Liang

Luke Zettlemoyer

Luke Zettlemoyer

University of Washington

Publications: 97

Christopher D. Manning

Christopher D. Manning

Stanford University

Publications: 83

Mohit Bansal

Mohit Bansal

University of North Carolina at Chapel Hill

Publications: 83

Jonathan Berant

Jonathan Berant

Tel Aviv University

Publications: 80

Graham Neubig

Graham Neubig

Carnegie Mellon University

Publications: 74

Jianfeng Gao

Jianfeng Gao

Microsoft (United States)

Publications: 71

Noah A. Smith

Noah A. Smith

University of Washington

Publications: 69

Dan Roth

Dan Roth

University of Pennsylvania

Publications: 63

Hannaneh Hajishirzi

Hannaneh Hajishirzi

University of Washington

Publications: 60

Daniel Klein

Daniel Klein

University of California, Berkeley

Publications: 58

Jason Weston

Jason Weston

Facebook (United States)

Publications: 57

Caiming Xiong

Caiming Xiong

Salesforce (United States)

Publications: 57

Mirella Lapata

Mirella Lapata

University of Edinburgh

Publications: 54

Richard Socher

Richard Socher

you.com

Publications: 54

Nan Duan

Nan Duan

Microsoft (United States)

Publications: 54

Ming Zhou

Ming Zhou

Sinovation Ventures

Publications: 51

Something went wrong. Please try again later.