What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Word, State and Margin.
His Artificial intelligence research incorporates themes from Pattern recognition, Speech recognition and Orders of magnitude.
His Speech recognition study incorporates themes from Word representation, Word lists by frequency and Word embedding.
His work in the fields of Language model and Syntactic structure overlaps with other areas such as Swahili and Hebrew.
There are a combination of areas like Analogy, Online encyclopedia and Quality integrated together with his Word study.
His State research includes themes of Translation and Inference.
His most cited work include:
- Enriching Word Vectors with Subword Information (4076 citations)
- Bag of Tricks for Efficient Text Classification (1501 citations)
- Learning Word Vectors for 157 Languages (439 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Natural language processing, Language model, Word and Machine learning.
His study ties his expertise on Pattern recognition together with the subject of Artificial intelligence.
Within one scientific family, he focuses on topics pertaining to Generative model under Natural language processing, and may sometimes address concerns connected to Syntax, Principle of compositionality and Latent variable.
His study in Language model is interdisciplinary in nature, drawing from both Transfer of learning, Cognitive psychology, Theoretical computer science and Transformer.
The concepts of his Word study are interwoven with issues in Representation, Translation and State.
His research investigates the connection between Machine learning and topics such as Class that intersect with problems in Binary classification.
He most often published in these fields:
- Artificial intelligence (70.65%)
- Natural language processing (32.61%)
- Language model (25.00%)
What were the highlights of his more recent work (between 2019-2021)?
- Question answering (10.87%)
- Transformer (15.22%)
- Artificial intelligence (70.65%)
In recent papers he was focusing on the following fields of study:
Edouard Grave mainly investigates Question answering, Transformer, Artificial intelligence, Machine translation and Information retrieval.
His research integrates issues of Language model, Algorithm, Quantization and Cross lingual in his study of Transformer.
His Artificial intelligence research is multidisciplinary, relying on both Machine learning and Natural language processing.
His Natural language processing research is multidisciplinary, incorporating elements of Translation and Training set.
His Machine translation study deals with Computation intersecting with Deep learning and Inference.
He has researched Information retrieval in several fields, including Artificial neural network and Generative grammar.
Between 2019 and 2021, his most popular works were:
- Unsupervised Cross-lingual Representation Learning at Scale (395 citations)
- Reducing Transformer Depth on Demand with Structured Dropout (97 citations)
- Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (54 citations)
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.
