What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
His main research concerns Artificial intelligence, Natural language processing, Coreference, Question answering and Information retrieval.
His studies examine the connections between Artificial intelligence and genetics, as well as such issues in Machine learning, with regards to Set.
His Natural language processing study frequently links to related topics such as Relation.
His Relation research includes elements of Knowledge management, Graphical model, Sentence and Knowledge base.
His Question answering study incorporates themes from WordNet, Boosting, World Wide Web and Falcon.
His work carried out in the field of Computational linguistics brings together such families of science as Parsing and Natural language.
His most cited work include:
- The Stanford CoreNLP Natural Language Processing Toolkit (4648 citations)
- Multi-instance Multi-label Learning for Relation Extraction (581 citations)
- The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies (447 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Natural language processing, Question answering, Machine learning and Information retrieval.
The various areas that he examines in his Artificial intelligence study include Domain and Event.
Natural language processing and Dependency are commonly linked in his work.
His research in Question answering intersects with topics in Context, Information needs, Load balancing and Transformer.
He combines subjects such as Training set and Set with his study of Machine learning.
His work in the fields of Open domain overlaps with other areas such as Baseline.
He most often published in these fields:
- Artificial intelligence (68.10%)
- Natural language processing (47.85%)
- Question answering (24.54%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (68.10%)
- Natural language processing (47.85%)
- Question answering (24.54%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Question answering, Sentence and Noun.
His research links Machine learning with Artificial intelligence.
His Natural language processing research is multidisciplinary, relying on both Context, Identification, Dependency, Named-entity recognition and Component.
The Question answering study combines topics in areas such as Selection, Transformer and Hop.
His Sentence study combines topics in areas such as Word and Reading comprehension.
In his study, Noun phrase is inextricably linked to Textual entailment, which falls within the broad field of Noun.
Between 2018 and 2021, his most popular works were:
- Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering (15 citations)
- Alignment over heterogeneous embeddings for question answering (15 citations)
- On the Importance of Delexicalization for Fact Verification (8 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
Mihai Surdeanu mainly focuses on Artificial intelligence, Natural language processing, Question answering, Sentence and Word.
His studies deal with areas such as Machine learning, Named-entity recognition and Geolocation as well as Artificial intelligence.
His Natural language processing research incorporates elements of SemEval, Suffix and Identification.
He undertakes interdisciplinary study in the fields of Question answering and Quality through his works.
He has researched Sentence in several fields, including Abstraction and Paragraph.
His Word study integrates concerns from other disciplines, such as Textual entailment and Noun, Noun phrase.
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.
