H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 87 Citations 29,740 391 World Ranking 312 National Ranking 193

Research.com Recognitions

Awards & Achievements

2014 - Fellow of the American Association for the Advancement of Science (AAAS)

2011 - ACM Fellow For contributions to machine learning and natural language processing.

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Programming language

Artificial intelligence, Machine learning, Natural language processing, Inference and Context are his primary areas of study. His study in Artificial intelligence is interdisciplinary in nature, drawing from both Set and Pattern recognition. Dan Roth works mostly in the field of Machine learning, limiting it down to concerns involving Training set and, occasionally, Grammar, Classifier, Error detection and correction and Range.

His studies deal with areas such as Textual entailment, Entity linking, Information retrieval and Hierarchical classifier as well as Natural language processing. His Inference study combines topics from a wide range of disciplines, such as F1 score, Relation, Linear programming, Semantic role labeling and Integer programming. His Context research is multidisciplinary, relying on both Annotation, Focus and Identification.

His most cited work include:

  • Design Challenges and Misconceptions in Named Entity Recognition (1097 citations)
  • Learning question classifiers (831 citations)
  • Learning to detect objects in images via a sparse, part-based representation (791 citations)

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

Dan Roth mainly focuses on Artificial intelligence, Natural language processing, Machine learning, Inference and Natural language. His study brings together the fields of Context and Artificial intelligence. His Natural language processing research incorporates elements of Named-entity recognition, Textual entailment, Word and Information retrieval.

His Machine learning study frequently involves adjacent topics like Training set. Much of his study explores Inference relationship to Theoretical computer science. His Semi-supervised learning study combines topics in areas such as Active learning and Algorithmic learning theory.

He most often published in these fields:

  • Artificial intelligence (73.24%)
  • Natural language processing (46.14%)
  • Machine learning (27.10%)

What were the highlights of his more recent work (between 2018-2021)?

  • Artificial intelligence (73.24%)
  • Natural language processing (46.14%)
  • Natural language (12.35%)

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

His primary areas of study are Artificial intelligence, Natural language processing, Natural language, Context and Named-entity recognition. He has included themes like Event and Machine learning in his Artificial intelligence study. His work in Machine learning addresses issues such as Inference, which are connected to fields such as Supervised learning.

The concepts of his Natural language processing study are interwoven with issues in Object, Scheme, Set and Coreference. His work on Natural language understanding as part of general Natural language study is frequently connected to Duration, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them. His study explores the link between Context and topics such as Structure that cross with problems in Structured prediction.

Between 2018 and 2021, his most popular works were:

  • Cross-Lingual Ability of Multilingual BERT: An Empirical Study (110 citations)
  • Question Answering as Global Reasoning Over Semantic Abstractions. (47 citations)
  • Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims. (42 citations)

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

  • Artificial intelligence
  • Machine learning
  • Programming language

Dan Roth mostly deals with Artificial intelligence, Natural language processing, Natural language, Named-entity recognition and Context. His Artificial intelligence study incorporates themes from Event and Machine learning. His studies in Machine learning integrate themes in fields like Relationship extraction and Word.

His Natural language processing study integrates concerns from other disciplines, such as Probabilistic logic, Set and Coreference. The study incorporates disciplines such as Window, World Wide Web and Supervised learning in addition to Natural language. The various areas that he examines in his Context study include Textual entailment, Hindi, Learning models, Empirical research and Conceptualization.

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

Design Challenges and Misconceptions in Named Entity Recognition

Lev Ratinov;Dan Roth.
conference on computational natural language learning (2009)

1415 Citations

Learning question classifiers

Xin Li;Dan Roth.
international conference on computational linguistics (2002)

1176 Citations

Learning to detect objects in images via a sparse, part-based representation

S. Agarwal;A. Awan;D. Roth.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2004)

1154 Citations

Emotions from Text: Machine Learning for Text-based Emotion Prediction

Cecilia Ovesdotter Alm;Dan Roth;Richard Sproat.
empirical methods in natural language processing (2005)

831 Citations

Local and Global Algorithms for Disambiguation to Wikipedia

Lev Ratinov;Dan Roth;Doug Downey;Mike Anderson.
meeting of the association for computational linguistics (2011)

750 Citations

Learning a Sparse Representation for Object Detection

Shivani Agarwal;Dan Roth.
european conference on computer vision (2002)

741 Citations

On the hardness of approximate reasoning

Dan Roth.
Artificial Intelligence (1996)

728 Citations

A SNoW-Based Face Detector

Ming-Hsuan Yang;Dan Roth;Narendra Ahuja.
neural information processing systems (1999)

536 Citations

The importance of syntactic parsing and inference in semantic role labeling

Vasin Punyakanok;Vasin Punyakanok;Vasin Punyakanok;Dan Roth;Dan Roth;Dan Roth;Wen-tau Yih;Wen-tau Yih;Wen-tau Yih.
Computational Linguistics (2008)

455 Citations

A Winnow-Based Approach to Context-Sensitive Spelling Correction

Andrew R. Golding;Dan Roth.
Machine Learning (1999)

435 Citations

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

Contact us

Best Scientists Citing Dan Roth

Jiawei Han

Jiawei Han

University of Illinois at Urbana-Champaign

Publications: 83

Andrew McCallum

Andrew McCallum

University of Massachusetts Amherst

Publications: 82

Alessandro Moschitti

Alessandro Moschitti

Amazon (United States)

Publications: 71

Heng Ji

Heng Ji

University of Illinois at Urbana-Champaign

Publications: 53

Gerhard Weikum

Gerhard Weikum

Max Planck Institute for Informatics

Publications: 51

Ido Dagan

Ido Dagan

Bar-Ilan University

Publications: 44

Thomas S. Huang

Thomas S. Huang

University of Illinois at Urbana-Champaign

Publications: 43

Guodong Zhou

Guodong Zhou

Soochow University

Publications: 40

Lise Getoor

Lise Getoor

University of California, Santa Cruz

Publications: 39

Pedro Domingos

Pedro Domingos

University of Washington

Publications: 39

Eyke Hüllermeier

Eyke Hüllermeier

Ludwig-Maximilians-Universität München

Publications: 38

Ting Liu

Ting Liu

Harbin Institute of Technology

Publications: 38

Luke Zettlemoyer

Luke Zettlemoyer

University of Washington

Publications: 36

Tarek Abdelzaher

Tarek Abdelzaher

University of Illinois at Urbana-Champaign

Publications: 36

Sebastian Riedel

Sebastian Riedel

University College London

Publications: 36

Lance Kaplan

Lance Kaplan

United States Army Research Laboratory

Publications: 35

Something went wrong. Please try again later.