What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Machine learning
His primary scientific interests are in Artificial intelligence, Natural language processing, Thin film, Machine learning and Analytical chemistry.
His Artificial intelligence study frequently draws connections between adjacent fields such as Pattern recognition.
His Natural language processing study combines topics from a wide range of disciplines, such as Annotation, Context, Speech recognition and Word.
His Thin film research incorporates elements of Optoelectronics, Doping, Molecular beam epitaxy, Epitaxy and Substrate.
Yuji Matsumoto has researched Machine learning in several fields, including Data mining and Identification.
His Analytical chemistry study incorporates themes from Magnetic semiconductor, Rutile and Exciton.
His most cited work include:
- Room-Temperature Ferromagnetism in Transparent Transition Metal-Doped Titanium Dioxide (2101 citations)
- Statistical Dependency Analysis with Support Vector Machines (587 citations)
- Applying Conditional Random Fields to Japanese Morphological Analysis (584 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Thin film, Analytical chemistry and Epitaxy.
The Artificial intelligence study combines topics in areas such as Speech recognition and Pattern recognition.
His study in Natural language processing is interdisciplinary in nature, drawing from both Dependency and Annotation.
His Thin film research includes themes of Optoelectronics, Substrate, Chemical engineering and Molecular beam epitaxy.
Yuji Matsumoto combines topics linked to Electron diffraction with his work on Analytical chemistry.
In most of his Epitaxy studies, his work intersects topics such as Crystallography.
He most often published in these fields:
- Artificial intelligence (41.92%)
- Natural language processing (34.44%)
- Thin film (15.80%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (41.92%)
- Natural language processing (34.44%)
- Ionic liquid (5.70%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Ionic liquid, Chemical engineering and Thin film.
Artificial intelligence and Pattern recognition are frequently intertwined in his study.
His research integrates issues of Tree and Annotation in his study of Natural language processing.
His Ionic liquid research includes elements of Chemical vapor deposition, Pentacene, Contact angle, Layer and Electrochemistry.
In his research on the topic of Thin film, Ellipsometry is strongly related with Analytical chemistry.
Yuji Matsumoto combines subjects such as Optoelectronics and Epitaxy with his study of Pulsed laser deposition.
Between 2016 and 2021, his most popular works were:
- Interpretable Adversarial Perturbation in Input Embedding Space for Text (59 citations)
- A Span Selection Model for Semantic Role Labeling (51 citations)
- Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach (50 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Natural language processing
His primary areas of study are Artificial intelligence, Natural language processing, Sentence, Dependency and Parsing.
The various areas that Yuji Matsumoto examines in his Artificial intelligence study include Machine learning and Pattern recognition.
Many of his studies on Natural language processing involve topics that are commonly interrelated, such as Tree.
His study explores the link between Tree and topics such as Construct that cross with problems in Dependency grammar.
The Sentence study combines topics in areas such as Image processing, Interpretability, Theoretical computer science and Word embedding.
Yuji Matsumoto interconnects Graph and Identification in the investigation of issues within Parsing.
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.
