What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Tie-Yan Liu focuses on Artificial intelligence, Machine learning, Learning to rank, Ranking and Information retrieval.
As part of his studies on Artificial intelligence, Tie-Yan Liu often connects relevant subjects like Natural language processing.
The various areas that Tie-Yan Liu examines in his Machine learning study include Event, Probabilistic logic and Data mining.
His Learning to rank research is multidisciplinary, relying on both Semi-supervised learning, Pairwise comparison, Ranking SVM and Benchmark.
His Ranking research focuses on subjects like Function, which are linked to Basis, Hessian matrix, Compensation and Stochastic gradient descent.
His work on Relevance as part of general Information retrieval study is frequently linked to Information storage, bridging the gap between disciplines.
His most cited work include:
- Learning to Rank for Information Retrieval (1780 citations)
- Learning to rank: from pairwise approach to listwise approach (1442 citations)
- LightGBM: a highly efficient gradient boosting decision tree (1214 citations)
What are the main themes of his work throughout his whole career to date?
Tie-Yan Liu spends much of his time researching Artificial intelligence, Machine learning, Machine translation, Information retrieval and Data mining.
Many of his studies on Artificial intelligence involve topics that are commonly interrelated, such as Natural language processing.
His Machine learning study combines topics in areas such as Training set and Benchmark.
Tie-Yan Liu has researched Machine translation in several fields, including Sentence, Speech recognition, Translation and Automatic summarization.
His research integrates issues of Web page and World Wide Web in his study of Information retrieval.
Ranking and Ranking are the subject areas of his Learning to rank study.
He most often published in these fields:
- Artificial intelligence (39.01%)
- Machine learning (19.80%)
- Machine translation (14.46%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (39.01%)
- Speech recognition (8.91%)
- Speech synthesis (4.95%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Speech recognition, Speech synthesis, Machine translation and Inference are his primary areas of study.
His Artificial intelligence research includes themes of Machine learning and Natural language processing.
The concepts of his Machine learning study are interwoven with issues in Contextual image classification, Training set and Benchmark.
His study in Speech recognition is interdisciplinary in nature, drawing from both Encoder and Context model.
His work carried out in the field of Machine translation brings together such families of science as Automatic summarization, Sequence, Natural language understanding and Transformer.
His Inference research incorporates elements of Software deployment and Autoregressive model.
Between 2019 and 2021, his most popular works were:
- Incorporating BERT into Neural Machine Translation (69 citations)
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (49 citations)
- On Layer Normalization in the Transformer Architecture (36 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His scientific interests lie mostly in Speech recognition, Artificial intelligence, Transformer, Speech synthesis and Machine translation.
His Artificial intelligence research integrates issues from Machine learning and Natural language processing.
His Machine learning study combines topics from a wide range of disciplines, such as Network architecture and Benchmark.
His studies deal with areas such as Normalization, Control theory, Embedding, Encoder and Initialization as well as Transformer.
His research in Speech synthesis intersects with topics in Quality, Inference and Autoregressive model.
Tie-Yan Liu combines subjects such as Langevin dynamics, Algorithm and Generative modeling with his study of Leverage.
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.
