What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Natural language processing
- Machine learning
Her scientific interests lie mostly in Artificial intelligence, Speech recognition, Natural language processing, Language model and Speech processing.
Her studies deal with areas such as Machine learning and Pattern recognition as well as Artificial intelligence.
Her Speech recognition research includes elements of Domain, Context, Discriminative model and Reduction.
Her work deals with themes such as Decision tree, Prosody, Speech synthesis and Set, which intersect with Natural language processing.
The various areas that Mari Ostendorf examines in her Language model study include Mixture model, Computational linguistics, Language identification and Cache language model.
Her Speech processing study incorporates themes from Response generation, Dialogue management and Error detection and correction.
Her most cited work include:
- TOBI: a standard for labeling English prosody. (650 citations)
- Segmental durations in the vicinity of prosodic phrase boundaries. (629 citations)
- From HMM's to segment models: a unified view of stochastic modeling for speech recognition (573 citations)
What are the main themes of her work throughout her whole career to date?
Artificial intelligence, Speech recognition, Natural language processing, Language model and Pattern recognition are her primary areas of study.
Mari Ostendorf interconnects Context, Machine learning and Vocabulary in the investigation of issues within Artificial intelligence.
Her Speech recognition research is multidisciplinary, incorporating elements of Word and Phrase.
Parsing, Sentence, Syntax, Spoken language and Information extraction are the subjects of her Natural language processing studies.
Her work carried out in the field of Language model brings together such families of science as Domain, Computational linguistics, Rank and Cache language model.
Her biological study spans a wide range of topics, including Estimation theory and Markov model.
She most often published in these fields:
- Artificial intelligence (61.89%)
- Speech recognition (55.68%)
- Natural language processing (40.27%)
What were the highlights of her more recent work (between 2014-2021)?
- Artificial intelligence (61.89%)
- Natural language processing (40.27%)
- Speech recognition (55.68%)
In recent papers she was focusing on the following fields of study:
Her primary areas of investigation include Artificial intelligence, Natural language processing, Speech recognition, Artificial neural network and Language model.
Specifically, her work in Artificial intelligence is concerned with the study of Reinforcement learning.
Mari Ostendorf has researched Natural language processing in several fields, including Conversation, SemEval and Training set.
Her Speech recognition study combines topics from a wide range of disciplines, such as Transcription, Word and Parsing.
Her Artificial neural network research integrates issues from Acoustic model and Robustness.
Her Perplexity study, which is part of a larger body of work in Language model, is frequently linked to Baseline, bridging the gap between disciplines.
Between 2014 and 2021, her most popular works were:
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction (159 citations)
- Deep Reinforcement Learning with a Natural Language Action Space (84 citations)
- A general framework for information extraction using dynamic span graphs (69 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
Mari Ostendorf mainly investigates Artificial intelligence, Natural language processing, Speech recognition, Recurrent neural network and Language model.
The Artificial intelligence study combines topics in areas such as Machine learning and Relevance.
The study incorporates disciplines such as Graph, Social media, Conversation and SemEval in addition to Natural language processing.
She does research in Speech recognition, focusing on Word error rate specifically.
Her work on Perplexity as part of her general Language model study is frequently connected to Community identity, thereby bridging the divide between different branches of science.
Her Transcription research includes themes of Prosody, Parsing, Sentence boundary disambiguation and Convolutional neural network.
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.
