H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 78 Citations 53,111 140 World Ranking 504 National Ranking 303

Research.com Recognitions

Awards & Achievements

2010 - ACM Fellow For contributions to machine-learning models of natural language and biological sequences.

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Programming language
  • Machine learning

Fernando Pereira focuses on Artificial intelligence, Natural language processing, Machine learning, Programming language and Parsing. The study of Artificial intelligence is intertwined with the study of Pattern recognition in a number of ways. His Natural language processing research is multidisciplinary, relying on both Speech recognition and Vector space model.

His Machine learning research is multidisciplinary, incorporating perspectives in Domain, Domain adaptation, Field and Test data. Fernando Pereira combines subjects such as Probabilistic logic and Sequence labeling with his study of Conditional random field. His Sequence labeling research includes themes of Structured prediction, Conditional entropy and Bayesian network.

His most cited work include:

  • Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data (11231 citations)
  • The information bottleneck method (1820 citations)
  • Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification (1700 citations)

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

Fernando Pereira spends much of his time researching Artificial intelligence, Natural language processing, Machine learning, Programming language and Natural language. His Artificial intelligence research includes elements of Speech recognition and Pattern recognition. His Pattern recognition research focuses on Discriminative model and Conditional random field.

His Natural language processing research is multidisciplinary, incorporating elements of Semantics, Bigram and Grammar. His work investigates the relationship between Bigram and topics such as Probabilistic logic that intersect with problems in Algorithm. Fernando Pereira studies Machine learning, namely Semi-supervised learning.

He most often published in these fields:

  • Artificial intelligence (50.61%)
  • Natural language processing (30.20%)
  • Machine learning (15.10%)

What were the highlights of his more recent work (between 2010-2020)?

  • Petri net (11.84%)
  • Artificial intelligence (50.61%)
  • Embedded system (7.76%)

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

Fernando Pereira focuses on Petri net, Artificial intelligence, Embedded system, Programming language and Code generation. The Petri net study combines topics in areas such as User interface, Software and Web application. His Artificial intelligence research incorporates themes from Machine learning, Pattern recognition and Natural language processing.

His Machine learning study incorporates themes from Classifier, Pose and Hidden Markov model. His study looks at the relationship between Programming language and fields such as XML, as well as how they intersect with chemical problems. His Algorithm study integrates concerns from other disciplines, such as Graphical model, Conditional random field, Markov model and Maximum-entropy Markov model.

Between 2010 and 2020, his most popular works were:

  • Large-Scale Cross-Document Coreference Using Distributed Inference and Hierarchical Models (114 citations)
  • Wikilinks: A Large-scale Cross-Document Coreference Corpus Labeled via Links to Wikipedia (85 citations)
  • Collective Entity Resolution with Multi-Focal Attention (84 citations)

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

  • Artificial intelligence
  • Programming language
  • Machine learning

Fernando Pereira spends much of his time researching Artificial intelligence, Programming language, Natural language processing, Petri net and Information retrieval. Fernando Pereira has researched Artificial intelligence in several fields, including Machine learning, Isolation, Speech recognition and Pattern recognition. His work in the fields of Graphical model overlaps with other areas such as Set.

In the subject of general Programming language, his work in Bottom-up parsing and Top-down parsing is often linked to Sling and Frame, thereby combining diverse domains of study. His study in Rule of inference extends to Natural language processing with its themes. His biological study spans a wide range of topics, including Microcontroller, Embedded system, User interface and Control theory.

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

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

John D. Lafferty;Andrew McCallum;Fernando C. N. Pereira.
international conference on machine learning (2001)

14581 Citations

The information bottleneck method

Naftali Tishby;Fernando C. N. Pereira;William Bialek.
Proc. 37th Annual Allerton Conference on Communications, Control and Computing, 1999 (2000)

2473 Citations

Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification

John Blitzer;Mark Dredze;Fernando Pereira.
meeting of the association for computational linguistics (2007)

2170 Citations

Shallow parsing with conditional random fields

Fei Sha;Fernando Pereira.
north american chapter of the association for computational linguistics (2003)

1846 Citations

Maximum Entropy Markov Models for Information Extraction and Segmentation

Andrew McCallum;Dayne Freitag;Fernando C. N. Pereira.
international conference on machine learning (2000)

1815 Citations

Definite clause grammars for language analysis—A survey of the formalism and a comparison with augmented transition networks

Fernando C.N. Pereira;David H.D. Warren.
Artificial Intelligence (1980)

1585 Citations

Domain Adaptation with Structural Correspondence Learning

John Blitzer;Ryan McDonald;Fernando Pereira.
empirical methods in natural language processing (2006)

1498 Citations

DISTRIBUTIONAL CLUSTERING OF ENGLISH WORDS

Fernando Pereira;Naftali Tishby;Lillian Lee.
meeting of the association for computational linguistics (1993)

1423 Citations

A theory of learning from different domains

Shai Ben-David;John Blitzer;Koby Crammer;Alex Kulesza.
Machine Learning (2010)

1260 Citations

The Unreasonable Effectiveness of Data

A. Halevy;P. Norvig;F. Pereira.
IEEE Intelligent Systems (2009)

1225 Citations

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

Contact us

Best Scientists Citing Fernando Pereira

Andrew McCallum

Andrew McCallum

University of Massachusetts Amherst

Publications: 138

Mehryar Mohri

Mehryar Mohri

Google (United States)

Publications: 112

Noah A. Smith

Noah A. Smith

University of Washington

Publications: 101

Asif Ekbal

Asif Ekbal

Indian Institute of Technology Patna

Publications: 80

Christopher D. Manning

Christopher D. Manning

Stanford University

Publications: 75

Joakim Nivre

Joakim Nivre

Uppsala University

Publications: 68

Jun'ichi Tsujii

Jun'ichi Tsujii

National Institute of Advanced Industrial Science and Technology

Publications: 63

Xiaolong Wang

Xiaolong Wang

Chinese Academy of Sciences

Publications: 62

Yuji Matsumoto

Yuji Matsumoto

Tohoku University

Publications: 62

Mark Johnson

Mark Johnson

Oracle (United States)

Publications: 61

Dan Roth

Dan Roth

University of Pennsylvania

Publications: 59

Sivaji Bandyopadhyay

Sivaji Bandyopadhyay

Jadavpur University

Publications: 56

Eric P. Xing

Eric P. Xing

Carnegie Mellon University

Publications: 55

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 55

Jason Eisner

Jason Eisner

Johns Hopkins University

Publications: 55

Sophia Ananiadou

Sophia Ananiadou

University of Manchester

Publications: 55

Something went wrong. Please try again later.