What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Linguistics
- Programming language
His main research concerns Artificial intelligence, Natural language processing, Parsing, Speech recognition and Pattern recognition.
His work investigates the relationship between Artificial intelligence and topics such as Machine learning that intersect with problems in Task.
His research in Natural language processing intersects with topics in Generative grammar, Set and Text segmentation.
His Set study also includes fields such as
- Noun which connect with Information retrieval,
- Coarse to fine that connect with fields like Statistical parsing.
His Parsing study integrates concerns from other disciplines, such as Tree, Sentence and Phrase structure rules.
Mark Johnson combines subjects such as Self training and Word with his study of Speech recognition.
His most cited work include:
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering (1510 citations)
- Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking (866 citations)
- SPICE: Semantic Propositional Image Caption Evaluation (641 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Natural language processing, Parsing, Speech recognition and Rule-based machine translation.
His Artificial intelligence research includes themes of Machine learning and Task.
He has included themes like Context, Probabilistic logic and Grammar in his Natural language processing study.
His work carried out in the field of Parsing brings together such families of science as Algorithm and Theoretical computer science.
His study in Rule-based machine translation focuses on L-attributed grammar in particular.
His research integrates issues of Bayesian probability and Vietnamese in his study of Text segmentation.
He most often published in these fields:
- Artificial intelligence (64.59%)
- Natural language processing (54.75%)
- Parsing (28.52%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (64.59%)
- Natural language processing (54.75%)
- Task (9.18%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Task, Parsing and Syntax.
His Artificial intelligence research incorporates themes from Domain, Machine learning and Function.
Mark Johnson has researched Natural language processing in several fields, including Word, Text segmentation and Closed captioning.
His biological study spans a wide range of topics, including Object and Object detection.
His studies in Task integrate themes in fields like Speech recognition and Benchmark.
His Syntax study combines topics from a wide range of disciplines, such as Representation, Semantic role labelling, Semantic role labeling and Data set.
Between 2017 and 2021, his most popular works were:
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering (1510 citations)
- Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (284 citations)
- AMR dependency parsing with a typed semantic algebra (47 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Linguistics
- Programming language
His primary scientific interests are in Artificial intelligence, Natural language processing, Task, Parsing and Object detection.
His work deals with themes such as Machine learning and Vietnamese, which intersect with Artificial intelligence.
His Natural language processing research is multidisciplinary, incorporating perspectives in Word, Text segmentation and Benchmark.
His biological study deals with issues like Function, which deal with fields such as Document classification.
His Parsing research includes elements of Dependency, Speech recognition, Type and Convolutional neural network.
His Visualization research incorporates elements of Question answering, Feature, Task analysis and Context model.
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.
