What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Stefan Riezler mostly deals with Artificial intelligence, Natural language processing, Parsing, Rule-based machine translation and Query language.
His research on Artificial intelligence often connects related topics like Pattern recognition.
His work on Lexicon as part of general Natural language processing study is frequently linked to Subcategorization, therefore connecting diverse disciplines of science.
His research investigates the connection between Parsing and topics such as Lexical functional grammar that intersect with issues in Speech recognition, Parser combinator and Top-down parsing.
His research investigates the connection between Rule-based machine translation and topics such as Ambiguity that intersect with problems in Lexicalization, German, Constraint and Log-linear model.
His Query language research is multidisciplinary, incorporating perspectives in Query expansion, Query optimization, Web query classification and Sargable.
His most cited work include:
- Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques (255 citations)
- Statistical Machine Translation for Query Expansion in Answer Retrieval (220 citations)
- On Some Pitfalls in Automatic Evaluation and Significance Testing for MT (168 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, Machine learning and Translation.
Stefan Riezler integrates Artificial intelligence and Quality in his research.
His work deals with themes such as Probabilistic logic, Grammar and German, which intersect with Natural language processing.
His research integrates issues of Information retrieval, Adaptation and Reinforcement learning in his study of Machine translation.
In the field of Machine learning, his study on Linear model overlaps with subjects such as Counterfactual thinking, Health care and Control variates.
His Translation study combines topics from a wide range of disciplines, such as Space and Component.
He most often published in these fields:
- Artificial intelligence (78.36%)
- Natural language processing (52.99%)
- Machine translation (43.28%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (78.36%)
- Machine translation (43.28%)
- Machine learning (21.64%)
In recent papers he was focusing on the following fields of study:
Stefan Riezler mainly investigates Artificial intelligence, Machine translation, Machine learning, Speech recognition and Natural language processing.
Borrowing concepts from Health care, Stefan Riezler weaves in ideas under Artificial intelligence.
His Machine translation study also includes
- SIGNAL, which have a strong connection to Structure, Maximum likelihood and Parsing,
- Robustness that connect with fields like Language model.
His Ground truth and Linear model study in the realm of Machine learning interacts with subjects such as Counterintuitive, Intensive care and Sepsis.
In his study, which falls under the umbrella issue of Speech recognition, Sentence, Direct speech, Component and German is strongly linked to Speech translation.
Stefan Riezler combines subjects such as Domain, Learning to rank, Ranking, Matching and Reinforcement learning with his study of Natural language processing.
Between 2018 and 2021, his most popular works were:
- Joey NMT: A Minimalist NMT Toolkit for Novices. (38 citations)
- LibriVoxDeEn - A Corpus for German-to-English Speech Translation and Speech Recognition (9 citations)
- Leveraging Implicit Expert Knowledge for Non-Circular Machine Learning in Sepsis Prediction (6 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Machine translation, Machine learning, Beam search and Ground truth.
His research brings together the fields of Structure and Artificial intelligence.
His research in Machine translation intersects with topics in Supervised training, Robustness and Sequence learning.
His Machine learning research incorporates themes from Maximum likelihood, SIGNAL and Parsing.
His Beam search investigation overlaps with other disciplines such as Human–computer interaction, Transformer, Imitation learning, Personalization and Reinforcement.
Ground truth is closely attributed to Linear model in his study.
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.
