What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Machine learning
Nan Duan mainly investigates Artificial intelligence, Question answering, Natural language processing, Information retrieval and Recurrent neural network.
Many of his studies on Artificial intelligence apply to Information flow as well.
Nan Duan has included themes like DUAL, Task analysis, Knowledge extraction, Scheme and Visualization in his Question answering study.
His Natural language processing research incorporates themes from Commonsense reasoning, Set and Transformer.
The various areas that Nan Duan examines in his Information retrieval study include Relation, Natural language and Chatbot.
His Recurrent neural network research is multidisciplinary, relying on both Question generation, Probabilistic logic and Leverage.
His most cited work include:
- Question Generation for Question Answering (135 citations)
- Question Answering and Question Generation as Dual Tasks (106 citations)
- Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training (98 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Natural language processing, Question answering, Information retrieval and Natural language.
Artificial intelligence is frequently linked to Machine learning in his study.
His work on Parsing as part of general Natural language processing study is frequently connected to Encoder, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Parsing study combines topics from a wide range of disciplines, such as Artificial neural network, Multi-task learning, SQL and Logical form.
His Question answering study combines topics in areas such as Question generation, Leverage and Knowledge base.
He has researched Benchmark in several fields, including Natural language understanding, Set and Task.
He most often published in these fields:
- Artificial intelligence (70.87%)
- Natural language processing (54.33%)
- Question answering (29.13%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (70.87%)
- Natural language processing (54.33%)
- Benchmark (10.24%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Natural language processing, Benchmark, Machine learning and Transformer.
His study in the field of Natural language and Question answering also crosses realms of Natural and Encoder.
His work carried out in the field of Question answering brings together such families of science as Dependency grammar, Information flow, Graph based and Knowledge base.
His Natural language processing study integrates concerns from other disciplines, such as Machine reading, Comprehension and Generative grammar.
In the subject of general Machine learning, his work in Overfitting is often linked to Base and Scale, thereby combining diverse domains of study.
His Transformer research includes themes of Language model, Rewriting, Layer and Continuous embedding.
Between 2019 and 2021, his most popular works were:
- K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters (76 citations)
- XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation (64 citations)
- Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training. (58 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Machine learning
Nan Duan mostly deals with Artificial intelligence, Natural language processing, Machine learning, Transformer and Benchmark.
Many of his research projects under Artificial intelligence are closely connected to Adapter with Adapter, tying the diverse disciplines of science together.
His studies deal with areas such as Inference, Graph based, Commonsense knowledge, Knowledge base and Information flow as well as Question answering.
His work on Natural language understanding as part of general Natural language processing research is frequently linked to Paragraph, bridging the gap between disciplines.
His Machine learning research integrates issues from n-gram and Automatic summarization.
The concepts of his Transformer study are interwoven with issues in Language model, Documentation and Natural language.
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.
