What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Operating system
- Machine learning
Yejin Choi mainly investigates Artificial intelligence, Natural language processing, Context, Natural language and Machine learning.
His research combines Quality and Artificial intelligence.
His research integrates issues of Checklist, Image and Internet privacy in his study of Natural language processing.
His Context research is multidisciplinary, incorporating elements of Question answering, News media, Dialog box and Reading comprehension.
His study in Machine learning is interdisciplinary in nature, drawing from both Context-free grammar and Stylometry.
His Language model study incorporates themes from Counterfactual conditional, Commonsense knowledge and Explicit knowledge.
His most cited work include:
- BabyTalk: Understanding and Generating Simple Image Descriptions (489 citations)
- Finding Deceptive Opinion Spam by Any Stretch of the Imagination (431 citations)
- OpinionFinder: A System for Subjectivity Analysis (416 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, Language model, Commonsense reasoning and Machine learning.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Context and Set.
His research in Natural language processing intersects with topics in Image and Reading comprehension.
His work in Language model tackles topics such as Commonsense knowledge which are related to areas like Knowledge graph.
The various areas that Yejin Choi examines in his Commonsense reasoning study include Crowdsourcing, Frame, Cognitive science and Human–computer interaction.
His work deals with themes such as Adversarial system and Benchmark, which intersect with Machine learning.
He most often published in these fields:
- Artificial intelligence (65.00%)
- Natural language processing (40.00%)
- Language model (29.17%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (65.00%)
- Language model (29.17%)
- Natural language processing (40.00%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Language model, Natural language processing, Commonsense reasoning and Machine learning are his primary areas of study.
His work in the fields of Artificial intelligence, such as Natural language, overlaps with other areas such as Transformer.
His Language model research includes elements of Transfer of learning, Decoding methods, Commonsense knowledge, Range and Natural language generation.
His Natural language processing research is multidisciplinary, relying on both Narrative, Interpretability, Image and Scripting language.
The Commonsense reasoning study combines topics in areas such as Inference, Question answering, Frame, Cognitive science and Generative grammar.
When carried out as part of a general Machine learning research project, his work on Overfitting and Leverage is frequently linked to work in Data mapping and Degeneration, therefore connecting diverse disciplines of study.
Between 2019 and 2021, his most popular works were:
- The Curious Case of Neural Text Degeneration (348 citations)
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale (104 citations)
- Abductive Commonsense Reasoning (83 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Operating system
Yejin Choi spends much of his time researching Artificial intelligence, Commonsense reasoning, Language model, Machine learning and Natural language processing.
His Statistical model and Word study are his primary interests in Artificial intelligence.
His Commonsense reasoning study combines topics in areas such as Inference, Question answering, Crowdsourcing, Generative grammar and Natural language.
The study incorporates disciplines such as Text corpus, Commonsense knowledge, Winograd Schema Challenge, Benchmark and Transfer of learning in addition to Language model.
His work on Overfitting and Leverage is typically connected to Data mapping and Degeneration as part of general Machine learning study, connecting several disciplines of science.
His studies deal with areas such as Object, Semantics, Image and Set as well as Natural language processing.
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.
