His main research concerns Artificial intelligence, Natural language processing, Parsing, Top-down parsing and Parser combinator. His Interpretation research extends to the thematically linked field of Artificial intelligence. His Natural language processing research includes themes of Context awareness, Pragmatics, Affective computing, Visualization and Feature extraction.
Kenji Sagae combines subjects such as Representation, Component and Measure with his study of Parsing. His study in LR parser and Top-down parsing language is done as part of Top-down parsing. His Canonical LR parser study deals with Simple LR parser intersecting with Speech recognition.
Kenji Sagae mainly focuses on Artificial intelligence, Natural language processing, Parsing, Speech recognition and Top-down parsing. In Artificial intelligence, Kenji Sagae works on issues like Task, which are connected to Isolation. The concepts of his Natural language processing study are interwoven with issues in Dependency and Domain.
His study looks at the relationship between Parsing and topics such as CHILDES, which overlap with Annotation, Ambiguity and Syntax. His work carried out in the field of Speech recognition brings together such families of science as Adaptation and Machine translation. His research is interdisciplinary, bridging the disciplines of Parser combinator and Top-down parsing.
Artificial intelligence, Natural language processing, Context, Natural language and Programming language are his primary areas of study. He interconnects Competence, Field, Spanish language and Written language in the investigation of issues within Artificial intelligence. He works on Natural language processing which deals in particular with Parsing.
Kenji Sagae has included themes like Second language, Language understanding and Heritage language in his Context study. His study looks at the relationship between Natural language and fields such as Set, as well as how they intersect with chemical problems. His research in Programming language intersects with topics in Argument, Grammar, Syntax and Reading.
His primary scientific interests are in Natural language processing, Artificial intelligence, Field, Spanish language and Encoder. His Encoder studies intersect with other subjects such as Feature engineering, Parsing, Graph and SemEval.
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.
Dependency Parsing and Domain Adaptation with LR Models and Parser Ensembles
Kenji Sagae;Jun'ichi Tsujii.
empirical methods in natural language processing (2007)
Dynamic Programming for Linear-Time Incremental Parsing
Liang Huang;Kenji Sagae.
meeting of the association for computational linguistics (2010)
YouTube Movie Reviews: Sentiment Analysis in an Audio-Visual Context
M. Wollmer;F. Weninger;T. Knaup;B. Schuller.
IEEE Intelligent Systems (2013)
Parser Combination by Reparsing
Kenji Sagae;Alon Lavie.
north american chapter of the association for computational linguistics (2006)
Evaluating contributions of natural language parsers to protein–protein interaction extraction
Yusuke Miyao;Kenji Sagae;Rune Sætre;Takuya Matsuzaki.
A Classifier-Based Parser with Linear Run-Time Complexity
Kenji Sagae;Alon Lavie.
international workshop/conference on parsing technologies (2005)
The significance of recall in automatic metrics for MT evaluation
Alon Lavie;Kenji Sagae;Shyamsundar Jayaraman.
conference of the association for machine translation in the americas (2004)
Syntactic Features for Protein-Protein Interaction Extraction.
Rune Sætre;Kenji Sagae;Jun'ichi Tsujii.
LBM (Short Papers) (2007)
Task-oriented Evaluation of Syntactic Parsers and Their Representations
Yusuke Miyao;Rune Saetre;Kenji Sagae;Takuya Matsuzaki.
meeting of the association for computational linguistics (2008)
Incremental interpretation and prediction of utterance meaning for interactive dialogue
David DeVault;Kenji Sagae;David R. Traum.
Dialogue & Discourse (2011)
If you think any of the details on this page are incorrect, let us know.
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: