What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
Artificial intelligence, Machine learning, Information retrieval, Natural language processing and World Wide Web are his primary areas of study.
His research integrates issues of Named-entity recognition and Graph in his study of Artificial intelligence.
His Machine learning research is multidisciplinary, incorporating elements of Classifier, Graph, Principle of maximum entropy and Multi-task learning.
His study on Recommender system is often connected to Heuristics as part of broader study in Information retrieval.
William W. Cohen has researched Natural language processing in several fields, including Feature engineering, Recurrent neural network and Categorization.
His studies in World Wide Web integrate themes in fields like Active learning, Instance-based learning, Set and Competence.
His most cited work include:
- Fast effective rule induction (3174 citations)
- A comparison of string distance metrics for name-matching tasks (1253 citations)
- Recommendation as classification: using social and content-based information in recommendation (872 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, Machine learning, Information retrieval and Theoretical computer science.
His study connects Graph and Artificial intelligence.
His Natural language processing research integrates issues from Context and Word.
The study incorporates disciplines such as Multi-task learning and Classifier in addition to Machine learning.
William W. Cohen combines subjects such as World Wide Web and Data mining with his study of Information retrieval.
His study in Theoretical computer science is interdisciplinary in nature, drawing from both Simple, Scalability and Learnability.
He most often published in these fields:
- Artificial intelligence (57.30%)
- Natural language processing (23.51%)
- Machine learning (23.24%)
What were the highlights of his more recent work (between 2014-2021)?
- Artificial intelligence (57.30%)
- Natural language processing (23.51%)
- Knowledge base (8.65%)
In recent papers he was focusing on the following fields of study:
William W. Cohen mainly focuses on Artificial intelligence, Natural language processing, Knowledge base, Question answering and Machine learning.
Language model, Word, Deep learning, Benchmark and Probabilistic logic are among the areas of Artificial intelligence where William W. Cohen concentrates his study.
The concepts of his Natural language processing study are interwoven with issues in Recurrent neural network, Graph, Reading comprehension, Task and Transfer of learning.
His biological study spans a wide range of topics, including Scalability, Theoretical computer science and Inference.
Question answering is a subfield of Information retrieval that William W. Cohen studies.
His work on Semi-supervised learning as part of general Machine learning research is frequently linked to Heuristics, thereby connecting diverse disciplines of science.
Between 2014 and 2021, his most popular works were:
- Revisiting semi-supervised learning with graph embeddings (493 citations)
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (424 citations)
- Never-ending learning (302 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
His primary areas of investigation include Artificial intelligence, Natural language processing, Machine learning, Question answering and Benchmark.
His study in Artificial intelligence concentrates on Embedding, Inference, Training set, Probabilistic logic and Treebank.
His research in Natural language processing intersects with topics in Recurrent neural network, Baseline, Character, Reading comprehension and Spelling.
His Machine learning research incorporates themes from Language model and Generative grammar.
His Question answering study is concerned with the larger field of Information retrieval.
In his work, Data mining is strongly intertwined with Generator, which is a subfield of Semi-supervised learning.
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.
