What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Natural language processing
- Machine learning
Her primary areas of study are Artificial intelligence, Natural language processing, Parsing, Question answering and Inference.
Her Pattern recognition research extends to Artificial intelligence, which is thematically connected.
Her work deals with themes such as Speech recognition and Word, which intersect with Natural language processing.
Her Parsing research integrates issues from Semantic role labeling and Natural language.
Her Question answering study combines topics in areas such as Natural language understanding and SemEval.
The various areas that Kristina Toutanova examines in her Inference study include Winograd Schema Challenge and Sequence labeling.
Her most cited work include:
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (15567 citations)
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (2654 citations)
- Feature-rich part-of-speech tagging with a cyclic dependency network (2474 citations)
What are the main themes of her work throughout her whole career to date?
Kristina Toutanova focuses on Artificial intelligence, Natural language processing, Machine translation, Parsing and Speech recognition.
Her Artificial intelligence study incorporates themes from Machine learning and Pattern recognition.
In her study, which falls under the umbrella issue of Natural language processing, Dependency is strongly linked to Set.
As a part of the same scientific family, she mostly works in the field of Machine translation, focusing on Syntax and, on occasion, BLEU.
Kristina Toutanova combines subjects such as Computational linguistics, Head-driven phrase structure grammar, Grammar, Selection and Natural language with her study of Parsing.
Her Language model research is multidisciplinary, relying on both Inference and Reading comprehension.
She most often published in these fields:
- Artificial intelligence (80.70%)
- Natural language processing (64.04%)
- Machine translation (20.18%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (80.70%)
- Question answering (12.28%)
- Natural language processing (64.04%)
In recent papers she was focusing on the following fields of study:
Artificial intelligence, Question answering, Natural language processing, Information retrieval and String are her primary areas of study.
Artificial intelligence is closely attributed to Machine learning in her work.
Kristina Toutanova focuses mostly in the field of Question answering, narrowing it down to topics relating to Context and, in certain cases, Paragraph, Sentiment analysis, Sentence and Automatic summarization.
Her research in Natural language processing is mostly focused on Language model.
In Language model, Kristina Toutanova works on issues like Reading comprehension, which are connected to Paraphrase, Transfer of learning, Logical consequence and Inference.
The Ranking research Kristina Toutanova does as part of her general Information retrieval study is frequently linked to other disciplines of science, such as Natural, Sequence and Autoregressive model, therefore creating a link between diverse domains of science.
Between 2018 and 2021, her most popular works were:
- Natural Questions: A Benchmark for Question Answering Research (429 citations)
- Latent Retrieval for Weakly Supervised Open Domain Question Answering (183 citations)
- Well-Read Students Learn Better: On the Importance of Pre-training Compact Models (99 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
Kristina Toutanova spends much of her time researching Artificial intelligence, Information retrieval, Question answering, Natural language processing and Machine learning.
In the subject of general Artificial intelligence, her work in Paraphrase, Logical consequence and Inference is often linked to Term and Meaning, thereby combining diverse domains of study.
Her study on Open domain is often connected to Natural as part of broader study in Information retrieval.
The study incorporates disciplines such as Search engine and Data set in addition to Question answering.
The Natural language processing study combines topics in areas such as Domain, Metadata, Reading, Construct and Entity linking.
Her research links Natural language with Machine 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.
