What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of study are Artificial intelligence, Natural language processing, Word, Machine learning and Machine translation.
Trevor Cohn integrates several fields in his works, including Artificial intelligence and Quality.
His studies deal with areas such as Exploit and Benchmark as well as Natural language processing.
His Word research is multidisciplinary, relying on both Lexical item, Similarity, Baseline and Component.
His Machine learning study incorporates themes from Social network, Named-entity recognition, Friendship and Cognitive reframing.
The Machine translation study which covers Translation that intersects with Phrase.
His most cited work include:
- DyNet: The Dynamic Neural Network Toolkit (337 citations)
- Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser (169 citations)
- Graph-to-Sequence Learning using Gated Graph Neural Networks (166 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Natural language processing, Machine learning, Machine translation and Word.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Speech recognition and Pattern recognition.
His work deals with themes such as Context and Transfer, which intersect with Natural language processing.
His work on Sentiment analysis as part of general Machine learning study is frequently connected to Gaussian process, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
The concepts of his Machine translation study are interwoven with issues in Grammar and Phrase.
Trevor Cohn interconnects Algorithm and Conditional random field in the investigation of issues within Inference.
He most often published in these fields:
- Artificial intelligence (64.63%)
- Natural language processing (36.99%)
- Machine learning (26.02%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (64.63%)
- Natural language processing (36.99%)
- Machine learning (26.02%)
In recent papers he was focusing on the following fields of study:
Trevor Cohn mainly focuses on Artificial intelligence, Natural language processing, Machine learning, Word and Machine translation.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Domain and Computer vision.
Trevor Cohn works in the field of Natural language processing, focusing on Parsing in particular.
The Stability research he does as part of his general Machine learning study is frequently linked to other disciplines of science, such as Training, therefore creating a link between diverse domains of science.
The Word study combines topics in areas such as Sentence, Pragmatics, Speech act and Oracle.
His studies in Machine translation integrate themes in fields like Computer security, Adversary and Training set.
Between 2018 and 2021, his most popular works were:
- Massively multilingual transfer for NER (44 citations)
- Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics (32 citations)
- Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation (25 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary scientific interests are in Artificial intelligence, Natural language processing, Named-entity recognition, Word and Machine learning.
In his study, Linguistic sequence complexity is strongly linked to Domain, which falls under the umbrella field of Artificial intelligence.
The study incorporates disciplines such as Context and Transfer in addition to Natural language processing.
His Named-entity recognition research includes elements of Event, Information extraction, Information retrieval and Key.
His studies deal with areas such as Sentence and Machine translation as well as Word.
He works mostly in the field of Machine learning, limiting it down to concerns involving Inference and, occasionally, Crowdsourcing, Benchmark, Graphical model, Conjugate prior and Bayesian probability.
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.
