What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
Mo Yu spends much of his time researching Artificial intelligence, Natural language processing, Question answering, Reading comprehension and Recurrent neural network.
His research in the fields of Entity linking overlaps with other disciplines such as Code.
His Natural language processing study combines topics in areas such as Embedding, Word, Convolutional neural network and Selection.
The Open domain research Mo Yu does as part of his general Question answering study is frequently linked to other disciplines of science, such as Pipeline, Rank and Component, therefore creating a link between diverse domains of science.
In Recurrent neural network, Mo Yu works on issues like State, which are connected to DUAL, Pattern recognition, Superresolution, Image and Benchmark.
His research integrates issues of Textual entailment, Regularization and SemEval in his study of Sentence.
His most cited work include:
- A Structured Self-attentive Sentence Embedding (677 citations)
- Target-dependent Twitter Sentiment Classification (592 citations)
- Comparative Study of CNN and RNN for Natural Language Processing (369 citations)
What are the main themes of his work throughout his whole career to date?
Mo Yu focuses on Artificial intelligence, Natural language processing, Machine learning, Question answering and Domain.
His work in Artificial intelligence addresses subjects such as Relationship extraction, which are connected to disciplines such as Named-entity recognition.
Mo Yu integrates many fields, such as Natural language processing and Reading comprehension, in his works.
His work carried out in the field of Question answering brings together such families of science as Semantic reasoner and Complex question.
In his study, Pattern recognition is strongly linked to Feature, which falls under the umbrella field of Word.
His study looks at the relationship between Embedding and fields such as Sentence, as well as how they intersect with chemical problems.
He most often published in these fields:
- Artificial intelligence (68.09%)
- Natural language processing (34.75%)
- Machine learning (24.11%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (68.09%)
- Question answering (19.15%)
- Natural language processing (34.75%)
In recent papers he was focusing on the following fields of study:
Mo Yu mainly investigates Artificial intelligence, Question answering, Natural language processing, Natural language and Theoretical computer science.
In the field of Artificial intelligence, his study on Natural language interaction and Interrogative word overlaps with subjects such as Domain, Interaction method and Product.
His Question answering research includes elements of Dependency, Benchmark and Complex question.
His Natural language processing research is multidisciplinary, incorporating perspectives in Word and Translation language.
His study explores the link between Natural language and topics such as Parsing that cross with problems in Relationship extraction, Representation, Relation and Ambiguity.
His research in Theoretical computer science focuses on subjects like Knowledge graph, which are connected to Small set.
Between 2019 and 2021, his most popular works were:
- Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation (20 citations)
- Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation (8 citations)
- Invariant Rationalization (6 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
His primary areas of investigation include Artificial intelligence, Question answering, Natural language processing, Object and Class.
His work deals with themes such as Relation and Ambiguity, which intersect with Artificial intelligence.
Mo Yu has researched Question answering in several fields, including Dependency, Theoretical computer science and Benchmark.
His studies deal with areas such as Word and Translation language as well as Natural language processing.
His Object research is multidisciplinary, relying on both Segmentation, Machine learning, Feature and Synthetic data.
His Feature research incorporates themes from Feature extraction and Pattern recognition.
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.
