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 45 Citations 9,430 152 World Ranking 3597 National Ranking 1842

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Programming language

Mohit Bansal mainly focuses on Artificial intelligence, Natural language processing, Word, Sentence and Machine learning. His work on Artificial intelligence deals in particular with Recurrent neural network, Natural language, Benchmark, Test set and Question answering. His study in the field of Parsing and Paraphrase is also linked to topics like Simple and Fraction.

His biological study spans a wide range of topics, including S-attributed grammar, Context, Speech recognition and Dependency grammar. His research investigates the link between Sentence and topics such as Inference that cross with problems in Encoding, Classifier and Generative model. His Machine learning study combines topics from a wide range of disciplines, such as Graph, Heuristics and Graph.

His most cited work include:

  • End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures (480 citations)
  • LXMERT: Learning Cross-Modality Encoder Representations from Transformers (357 citations)
  • Towards Universal Paraphrastic Sentence Embeddings (348 citations)

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

His primary areas of investigation include Artificial intelligence, Natural language processing, Machine learning, Natural language and Question answering. As part of his studies on Artificial intelligence, Mohit Bansal often connects relevant subjects like Context. His work is dedicated to discovering how Natural language processing, Logical consequence are connected with Closed captioning and other disciplines.

His Machine learning research is multidisciplinary, relying on both Adversarial system, Inference and Benchmark. His study in Natural language is interdisciplinary in nature, drawing from both Comprehension, Robot, Theoretical computer science and Human–computer interaction. His studies in Question answering integrate themes in fields like Modality, Image and Training set.

He most often published in these fields:

  • Artificial intelligence (68.31%)
  • Natural language processing (37.86%)
  • Machine learning (26.34%)

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

  • Artificial intelligence (68.31%)
  • Machine learning (26.34%)
  • Natural language processing (37.86%)

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

Artificial intelligence, Machine learning, Natural language processing, Code and Language model are his primary areas of study. His Artificial intelligence study frequently involves adjacent topics like Context. His Machine learning research is multidisciplinary, incorporating elements of Domain, Variety and Inference.

His studies deal with areas such as Modality, Conversation and Coreference as well as Natural language processing. The various areas that Mohit Bansal examines in his Language model study include Code, Semantics, Control and Predicate. In his research on the topic of Sentence, Semi-supervised learning is strongly related with Endangered language.

Between 2019 and 2021, his most popular works were:

  • Adversarial NLI: A New Benchmark for Natural Language Understanding (103 citations)
  • TVQA+: Spatio-Temporal Grounding for Video Question Answering (50 citations)
  • Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? (19 citations)

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

  • Artificial intelligence
  • Machine learning
  • Programming language

Mohit Bansal spends much of his time researching Artificial intelligence, Natural language processing, Machine learning, Closed captioning and Code. His Artificial intelligence research incorporates themes from Context and Orthogonality. His work deals with themes such as Set and Robustness, which intersect with Natural language processing.

The study incorporates disciplines such as Domain, Variety, Debiasing and Embedding in addition to Machine learning. Mohit Bansal interconnects Paragraph, Transformer, Window, Sentence and Coreference in the investigation of issues within Closed captioning. The concepts of his Question answering study are interwoven with issues in Classifier and Intelligent decision support system.

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

End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures

Makoto Miwa;Mohit Bansal.
meeting of the association for computational linguistics (2016)

539 Citations

Towards Universal Paraphrastic Sentence Embeddings

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

382 Citations

LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Hao Tan;Mohit Bansal.
empirical methods in natural language processing (2019)

357 Citations

Tailoring Continuous Word Representations for Dependency Parsing

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

343 Citations

What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment

Hongyuan Mei;Mohit Bansal;Matthew R. Walter.
north american chapter of the association for computational linguistics (2016)

311 Citations

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

Yen-Chun Chen;Mohit Bansal.
meeting of the association for computational linguistics (2018)

275 Citations

From Paraphrase Database to Compositional Paraphrase Model and Back

John Wieting;Mohit Bansal;Kevin Gimpel;Karen Livescu.
Transactions of the Association for Computational Linguistics (2015)

254 Citations

MAttNet: Modular Attention Network for Referring Expression Comprehension

Licheng Yu;Zhe Lin;Xiaohui Shen;Jimei Yang.
computer vision and pattern recognition (2018)

243 Citations

What Are You Talking About? Text-to-Image Coreference

Chen Kong;Dahua Lin;Mohit Bansal;Raquel Urtasun.
computer vision and pattern recognition (2014)

179 Citations

A Joint Speaker-Listener-Reinforcer Model for Referring Expressions

Licheng Yu;Hao Tan;Mohit Bansal;Tamara L. Berg.
computer vision and pattern recognition (2017)

176 Citations

Best Scientists Citing Mohit Bansal

Devi Parikh

Devi Parikh

Facebook (United States)

Publications: 47

Jianfeng Gao

Jianfeng Gao

Microsoft (United States)

Publications: 46

Yejin Choi

Yejin Choi

Allen Institute for Artificial Intelligence

Publications: 43

Kevin Gimpel

Kevin Gimpel

Toyota Technological Institute at Chicago

Publications: 41

Dhruv Batra

Dhruv Batra

Georgia Institute of Technology

Publications: 41

Anna Korhonen

Anna Korhonen

University of Cambridge

Publications: 36

Maosong Sun

Maosong Sun

Tsinghua University

Publications: 35

William Yang Wang

William Yang Wang

University of California, Santa Barbara

Publications: 34

Graham Neubig

Graham Neubig

Carnegie Mellon University

Publications: 34

Dan Roth

Dan Roth

University of Pennsylvania

Publications: 33

Jonathan Berant

Jonathan Berant

Tel Aviv University

Publications: 33

Caiming Xiong

Caiming Xiong

Salesforce (United States)

Publications: 32

Ivan Vulić

Ivan Vulić

University of Cambridge

Publications: 32

Zhe Gan

Zhe Gan

Microsoft (United States)

Publications: 31

Daniel Klein

Daniel Klein

University of California, Berkeley

Publications: 30

Noah A. Smith

Noah A. Smith

University of Washington

Publications: 30

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.