What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Natural language processing
- Programming language
Dragomir R. Radev mainly investigates Artificial intelligence, Information retrieval, Automatic summarization, Natural language processing and Multi-document summarization.
Dragomir R. Radev studies Artificial intelligence, namely Cosine similarity.
His Information retrieval research is multidisciplinary, relying on both Cohesion, Computational linguistics, Set and Citation.
The concepts of his Automatic summarization study are interwoven with issues in Sentence, Prestige, World Wide Web and Cluster analysis.
The Natural language processing study combines topics in areas such as Graph and Taxonomy.
His Multi-document summarization study incorporates themes from Paraphrase, Identity and Identification.
His most cited work include:
- LexRank: graph-based lexical centrality as salience in text summarization (1906 citations)
- Centroid-based summarization of multiple documents (860 citations)
- TimeML: Robust Specification of Event and Temporal Expressions in Text (596 citations)
What are the main themes of his work throughout his whole career to date?
Dragomir R. Radev spends much of his time researching Artificial intelligence, Natural language processing, Information retrieval, Automatic summarization and Question answering.
Dragomir R. Radev focuses mostly in the field of Artificial intelligence, narrowing it down to topics relating to Graph and, in certain cases, Centrality.
His study looks at the relationship between Natural language processing and fields such as Domain, as well as how they intersect with chemical problems.
Within one scientific family, Dragomir R. Radev focuses on topics pertaining to Citation under Information retrieval, and may sometimes address concerns connected to Field.
His studies in Automatic summarization integrate themes in fields like Salient, Lexical similarity and World Wide Web.
His work deals with themes such as Document retrieval and Search engine, which intersect with Question answering.
He most often published in these fields:
- Artificial intelligence (57.61%)
- Natural language processing (47.83%)
- Information retrieval (40.94%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (57.61%)
- Natural language processing (47.83%)
- Information retrieval (40.94%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Natural language processing, Information retrieval, Domain and SQL.
His work on Artificial intelligence is being expanded to include thematically relevant topics such as Machine learning.
His Natural language processing research includes elements of Dependency, Context, Word and Deep learning.
His study in the field of Information extraction is also linked to topics like Key.
His research integrates issues of Natural language, Task and Test set in his study of SQL.
His primary area of study in Automatic summarization is in the field of Multi-document summarization.
Between 2015 and 2021, his most popular works were:
- TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation (101 citations)
- Improving Text-to-SQL Evaluation Methodology. (97 citations)
- Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (94 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Natural language processing
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Information retrieval, SQL and Automatic summarization.
His research related to Sentence, Coreference and Artificial neural network might be considered part of Artificial intelligence.
The Natural language processing study combines topics in areas such as Context, Antecedent, Resolution and Cluster analysis.
His Information retrieval research includes elements of Computational linguistics and Benchmark.
His research in SQL intersects with topics in Domain, Machine learning, Test set and Natural language.
His research on Automatic summarization focuses in particular on Multi-document summarization.
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.
