What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Inference, Machine translation and Encoder.
His Artificial intelligence research includes elements of Latent class model and Machine learning.
His work carried out in the field of Natural language processing brings together such families of science as Feature and Statistical model.
His Inference study incorporates themes from Question answering, Theoretical computer science and Parsing.
His work deals with themes such as Relational database and Knowledge base, which intersect with Question answering.
As a part of the same scientific family, Ivan Titov mostly works in the field of Knowledge base, focusing on Artificial neural network and, on occasion, Speech recognition.
His most cited work include:
- Modeling Relational Data with Graph Convolutional Networks (1014 citations)
- Modeling Relational Data with Graph Convolutional Networks (1014 citations)
- Modeling online reviews with multi-grain topic models (618 citations)
What are the main themes of his work throughout his whole career to date?
Ivan Titov mainly focuses on Artificial intelligence, Natural language processing, Machine translation, Parsing and Machine learning.
Semantic role labeling, Latent variable, Inference, Syntax and Natural language are among the areas of Artificial intelligence where Ivan Titov concentrates his study.
His Inference research incorporates elements of Question answering and Theoretical computer science.
His work on Sentence, Automatic summarization and Language model as part of general Natural language processing study is frequently linked to Component, bridging the gap between disciplines.
The various areas that Ivan Titov examines in his Machine translation study include Encoder, Decoding methods, Transformer and Training set.
Ivan Titov does research in Machine learning, focusing on Artificial neural network specifically.
He most often published in these fields:
- Artificial intelligence (80.75%)
- Natural language processing (58.39%)
- Machine translation (22.98%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (80.75%)
- Natural language processing (58.39%)
- Machine translation (22.98%)
In recent papers he was focusing on the following fields of study:
Ivan Titov mainly investigates Artificial intelligence, Natural language processing, Machine translation, Language model and Training set.
Ivan Titov frequently studies issues relating to Machine learning and Artificial intelligence.
His Machine learning research is multidisciplinary, relying on both Prefix and Normalization.
As part of his studies on Natural language processing, he frequently links adjacent subjects like Inference.
His Machine translation research focuses on Decoding methods and how it relates to Encoder and Word.
Ivan Titov combines subjects such as Minimum description length, Word-sense disambiguation, Adversarial system and Source text with his study of Training set.
Between 2019 and 2021, his most popular works were:
- Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation (29 citations)
- Information-Theoretic Probing with Minimum Description Length (20 citations)
- Unsupervised Opinion Summarization as Copycat-Review Generation (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Artificial intelligence, Natural language processing, Training set, Machine translation and Pattern recognition are his primary areas of study.
His work on Artificial intelligence deals in particular with Enhanced Data Rates for GSM Evolution, Classifier, Language model, Syntax and Parsing.
In the subject of general Natural language processing, his work in Semantic role labeling and Question answering is often linked to Norm and Simple, thereby combining diverse domains of study.
Ivan Titov usually deals with Training set and limits it to topics linked to Generative model and Automatic summarization.
His Automatic summarization research includes themes of Encoder, Decoding methods, Transformer and Word lists by frequency.
His Machine translation research integrates issues from Algorithm, Translation, Shot and Zero.
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.
