What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Natural language processing
Eduard Hovy spends much of his time researching Artificial intelligence, Natural language processing, Information retrieval, Question answering and Automatic summarization.
His Artificial intelligence study combines topics in areas such as Machine learning and Task.
His research in Natural language processing intersects with topics in Variety, Word and Coreference.
The various areas that Eduard Hovy examines in his Information retrieval study include Matching, Computational linguistics and Identification.
His Question answering research is multidisciplinary, incorporating perspectives in Simple, State and Art history.
His work on Text graph and Multi-document summarization as part of general Automatic summarization study is frequently linked to Ideal, bridging the gap between disciplines.
His most cited work include:
- Hierarchical Attention Networks for Document Classification (2218 citations)
- Determining the sentiment of opinions (1210 citations)
- End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF (1197 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, Information retrieval, Task and Machine translation.
Artificial intelligence is often connected to Machine learning in his work.
His Natural language processing research incorporates elements of Annotation, Semantics and Context.
His research on Information retrieval frequently connects to adjacent areas such as World Wide Web.
He regularly ties together related areas like Quality in his Machine translation studies.
Eduard Hovy is interested in Multi-document summarization, which is a branch of Automatic summarization.
He most often published in these fields:
- Artificial intelligence (56.26%)
- Natural language processing (44.07%)
- Information retrieval (19.53%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (56.26%)
- Natural language processing (44.07%)
- Task (12.52%)
In recent papers he was focusing on the following fields of study:
Eduard Hovy mainly focuses on Artificial intelligence, Natural language processing, Task, Machine learning and Sentence.
Eduard Hovy interconnects Quality, Argument and Pattern recognition in the investigation of issues within Artificial intelligence.
Eduard Hovy specializes in Natural language processing, namely Parsing.
He combines subjects such as Class, Context, Natural language and Set with his study of Task.
His Machine learning study combines topics from a wide range of disciplines, such as Layer, Noise and Word error rate.
His Sentence study integrates concerns from other disciplines, such as Digital media, Feature engineering, Fake news and Code.
Between 2017 and 2021, his most popular works were:
- Self-Training With Noisy Student Improves ImageNet Classification (328 citations)
- Unsupervised Data Augmentation for Consistency Training. (311 citations)
- Unsupervised Data Augmentation (148 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Machine learning
Eduard Hovy focuses on Artificial intelligence, Natural language processing, Task, Machine learning and Word.
Much of his study explores Artificial intelligence relationship to Pattern recognition.
His work carried out in the field of Natural language processing brings together such families of science as Recurrent neural network, Baseline, Textual entailment, Representation and Coreference.
His research integrates issues of Sentiment analysis, Counterfactual thinking, Causality and Spurious relationship in his study of Task.
He works mostly in the field of Machine learning, limiting it down to concerns involving Quality and, occasionally, Flexibility, BLEU, Face and Maximum likelihood.
His Word research incorporates themes from Embedding, Meaning and Set.
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.
