What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Machine learning
Kevin Duh mainly focuses on Artificial intelligence, Natural language processing, Machine learning, Machine translation and Word.
Kevin Duh performs multidisciplinary study in Artificial intelligence and Quality in his work.
His studies deal with areas such as Context and Speech recognition as well as Natural language processing.
In his research, Word error rate is intimately related to Arabic, which falls under the overarching field of Speech recognition.
Kevin Duh has included themes like Domain adaptation, Parsing and Adaptation in his Machine translation study.
His Word research integrates issues from Preprocessor, BLEU, Set, Head and Syntax.
His most cited work include:
- DyNet: The Dynamic Neural Network Toolkit (337 citations)
- Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval (248 citations)
- Automatic Evaluation of Translation Quality for Distant Language Pairs (240 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 translation, Machine learning and Word.
His Artificial intelligence study frequently links to other fields, such as Speech recognition.
The various areas that Kevin Duh examines in his Natural language processing study include Annotation and Arabic.
His Machine translation research is multidisciplinary, incorporating elements of Domain, Initialization and Rule-based machine translation.
Kevin Duh interconnects Training set and Inference in the investigation of issues within Machine learning.
As a member of one scientific family, Kevin Duh mostly works in the field of Word, focusing on Convolutional neural network and, on occasion, Spelling.
He most often published in these fields:
- Artificial intelligence (80.10%)
- Natural language processing (56.63%)
- Machine translation (40.82%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (80.10%)
- Machine translation (40.82%)
- Natural language processing (56.63%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Machine translation, Natural language processing, Machine learning and Translation.
His work on Artificial intelligence is being expanded to include thematically relevant topics such as State.
His Machine translation research is multidisciplinary, incorporating perspectives in Domain, Domain adaptation, Embedding and Initialization.
The Natural language processing study combines topics in areas such as End-to-end principle, Arabic and Meaning.
In the subject of general Machine learning, his work in Hyperparameter, Deep learning and Artificial neural network is often linked to Sample, thereby combining diverse domains of study.
Kevin Duh usually deals with Parsing and limits it to topics linked to Transduction and Graph and Speech recognition.
Between 2017 and 2021, his most popular works were:
- Stochastic Answer Networks for Machine Reading Comprehension (120 citations)
- ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension. (116 citations)
- Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation (68 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
His primary areas of study are Artificial intelligence, Machine translation, Natural language processing, Machine learning and Comprehension.
His Artificial intelligence study combines topics in areas such as Field and State.
His Machine translation study incorporates themes from Domain adaptation, Domain and Initialization.
His Natural language processing research incorporates themes from Translation and Coreference.
Kevin Duh works mostly in the field of Machine learning, limiting it down to topics relating to BLEU and, in certain cases, Word and Cross entropy.
His Comprehension research focuses on Question answering and how it connects with Machine reading, Reinforcement learning, Robustness and Artificial neural network.
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.
