World's Best Scientists 2026 revealed!
Miguel Ballesteros

Miguel Ballesteros

Overview

Miguel Ballesteros is affiliated with Oracle (US) in the United States. Their research is primarily situated within computer science, with a significant emphasis on artificial intelligence. The scientist's work spans several subfields including information systems, computer networks and communications, as well as computer vision and pattern recognition.

Their scholarly output covers numerous topics linked to natural language processing and text analysis, including:

  • Topic Modeling
  • Natural Language Processing Techniques
  • Advanced Text Analysis Techniques
  • Text and Document Classification Technologies
  • Speech Recognition and Synthesis
  • Speech and Dialogue Systems
  • Domain Adaptation and Few-Shot Learning

Miguel Ballesteros has contributed to a variety of publication venues. Most frequently, their work appears in:

  • arXiv (Cornell University)
  • Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
  • Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • Zenodo (CERN European Organization for Nuclear Research)
  • HAL (Le Centre pour la Communication Scientifique Directe)

Some of their notable recent papers include:

  • Universal Dependencies, 2025, HAL (Le Centre pour la Communication Scientifique Directe)
  • How much pretraining data do language models need to learn syntax?, 2021, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
  • Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning, 2022, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
  • On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations, 2021, Zenodo (CERN European Organization for Nuclear Research)
  • General Purpose Verification for Chain of Thought Prompting, 2024, arXiv (Cornell University)

The scientist regularly collaborates with several co-authors. Frequent collaborators include:

  • Yassine Benajiba
  • Neha Anna John
  • Shuai Wang
  • Yogarshi Vyas
  • Jie Ma

Best Publications

  • Neural Architectures for Named Entity Recognition

    Guillaume Lample;Miguel Ballesteros;Sandeep Subramanian;Kazuya Kawakami

  • Transition-Based Dependency Parsing with Stack Long Short-Term Memory

    Chris Dyer;Miguel Ballesteros;Wang Ling;Austin Matthews

  • Universal Dependencies 2.2

    Joakim Nivre;Mitchell Abrams;Željko Agić;Lars Ahrenberg

  • Recurrent Neural Network Grammars

    Chris Dyer;Adhiguna Kuncoro;Miguel Ballesteros;Noah A. Smith

  • DyNet: The Dynamic Neural Network Toolkit

    Graham Neubig;Chris Dyer;Yoav Goldberg;Austin Matthews

  • Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs

    Miguel Ballesteros;Chris Dyer;Noah A. Smith

  • Many Languages, One Parser

    Waleed Ammar;George Mulcaire;Miguel Ballesteros;Miguel Ballesteros;Chris Dyer

  • Universal Dependencies 2.1

    Joakim Nivre;Željko Agić;Lars Ahrenberg;Lene Antonsen

  • Universal Dependencies 2.0

    Joakim Nivre;Željko Agić;Lars Ahrenberg;Maria Jesus Aranzabe

  • Universal Dependencies 2.3

    Joakim Nivre;Mitchell Abrams;Željko Agić;Lars Ahrenberg

  • Universal Dependencies 1.2

    Joakim Nivre;Željko Agić;Maria Jesus Aranzabe;Masayuki Asahara

  • Detecting readers with dyslexia using machine learning with eye tracking measures

    Luz Rello;Miguel Ballesteros

  • What Do Recurrent Neural Network Grammars Learn About Syntax

    Adhiguna Kuncoro;Miguel Ballesteros;Lingpeng Kong;Chris Dyer

  • Neural language models as psycholinguistic subjects: Representations of syntactic state.

    Richard Futrell;Ethan Wilcox;Takashi Morita;Peng Qian

  • SemEval 2018 Task 2: multilingual emoji prediction

    Francesco Barbieri;Jose Camacho-Collados;Francesco Ronzano;Luis Espinosa Anke

  • Are Emojis Predictable

    Francesco Barbieri;Miguel Ballesteros;Horacio Saggion

  • Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser

    Adhiguna Kuncoro;Miguel Ballesteros;Lingpeng Kong;Chris Dyer

  • MaltOptimizer: An Optimization Tool for MaltParser

    Miguel Ballesteros;Joakim Nivre

  • Training with Exploration Improves a Greedy Stack LSTM Parser

    Miguel Ballesteros;Yoav Goldberg;Chris Dyer;Noah A. Smith

  • Universal Dependencies 2.7

    Daniel Zeman;Joakim Nivre;Mitchell Abrams;Elia Ackermann

Frequent Co-Authors

Joakim Nivre
Joakim Nivre Uppsala University
Noah A. Smith
Noah A. Smith University of Washington
Christopher D. Manning
Christopher D. Manning Stanford University
Chris Dyer
Chris Dyer Google (United States)
Filip Ginter
Filip Ginter University of Turku
Samuel R. Bowman
Samuel R. Bowman New York University
Sampo Pyysalo
Sampo Pyysalo University of Turku
Jan Hajič
Jan Hajič Charles University
Barbara Plank
Barbara Plank Ludwig-Maximilians-Universität München

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

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Pursuing Computer Science in the USA opens up a wide range of online degree and career options. It's important to consider flexibility, affordability, and your academic background when choosing a program. For students exploring advanced credentials, understanding which master's degree is most in demand in USA can help guide your career trajectory. A relevant, in-demand master's can boost your job prospects and salary potential.

If you're starting your studies or prefer a shorter commitment, an associate degree online offers flexibility and a quicker route into tech careers. For budget-conscious learners, exploring the cheapest online college options can make higher education more accessible without compromising on quality.

Not all paths require a perfect academic record. There are excellent options for those who need a second chance—check out college that accepts low gpa to find supportive institutions that can help you launch a successful career in tech.

Best Scientists Citing Miguel Ballesteros

Trending Scientists

Recently Published Articles