What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
Michael Auli mostly deals with Artificial intelligence, Recurrent neural network, Language model, Translation and Machine translation.
His studies in Artificial intelligence integrate themes in fields like Machine learning and Natural language processing.
Michael Auli works mostly in the field of Language model, limiting it down to topics relating to Automatic summarization and, in certain cases, Extensibility, Inference and Programming language.
The study incorporates disciplines such as Layer and Sequence learning in addition to Translation.
His Layer research integrates issues from Algorithm, Computation and Convolutional neural network.
His work in Machine translation covers topics such as Test set which are related to areas like SIGNAL and Acoustic model.
His most cited work include:
- Convolutional sequence to sequence learning (1236 citations)
- Language modeling with gated convolutional networks (781 citations)
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling (768 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 translation, Language model and Speech recognition.
His study explores the link between Artificial intelligence and topics such as Machine learning that cross with problems in Training set.
He has included themes like Domain, Generative grammar and Transformer in his Natural language processing study.
His study looks at the relationship between Machine translation and topics such as Algorithm, which overlap with Convolution and Convolutional neural network.
His Language model research incorporates elements of Question answering, Inference and Automatic summarization.
His Translation study incorporates themes from Benchmark and Sequence learning.
He most often published in these fields:
- Artificial intelligence (63.46%)
- Natural language processing (30.77%)
- Machine translation (29.81%)
What were the highlights of his more recent work (between 2020-2021)?
- Artificial intelligence (63.46%)
- Machine translation (29.81%)
- Speech recognition (24.04%)
In recent papers he was focusing on the following fields of study:
His main research concerns Artificial intelligence, Machine translation, Speech recognition, Labeled data and Feature learning.
Artificial intelligence is closely attributed to Natural language processing in his work.
His Document level and Language model study, which is part of a larger body of work in Natural language processing, is frequently linked to Simple, Work and Scale, bridging the gap between disciplines.
His studies deal with areas such as Language modelling, Variety and Transformer as well as Machine translation.
His research integrates issues of Phoneme recognition, Quantization, Speech processing, Word error rate and Deep learning in his study of Feature learning.
His Word error rate research includes elements of SIGNAL, Latent variable and Cross lingual.
Between 2020 and 2021, his most popular works were:
- Unsupervised Cross-lingual Representation Learning for Speech Recognition (27 citations)
- Self-Training and Pre-Training are Complementary for Speech Recognition (1 citations)
- A Comparison of Discrete Latent Variable Models for Speech Representation Learning (0 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
His primary scientific interests are in Speech recognition, Feature learning, Word error rate, Training and Labeled data.
The study of Speech recognition is intertwined with the study of Quantization in a number of ways.
His work carried out in the field of Quantization brings together such families of science as Deep learning, Speech processing, Cross lingual and Artificial intelligence.
Among his Training studies, there is a synthesis of other scientific areas such as Self training and Test.
Structure combines with fields such as Latent variable, SIGNAL, Phoneme recognition and ABX test in his investigation.
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.
