What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Natural language processing
- Machine learning
Dilek Hakkani-Tur mainly focuses on Artificial intelligence, Natural language processing, Speech recognition, Spoken language and Natural language.
Her Artificial intelligence research is multidisciplinary, incorporating perspectives in Machine learning and Set.
Her Natural language processing research includes elements of Context, Spoken dialog systems, Dialog system and Utterance.
Dilek Hakkani-Tur has researched Speech recognition in several fields, including Sentence, Segmentation, Unsupervised learning and Feature extraction.
Her biological study spans a wide range of topics, including Recurrent neural network, Computational linguistics, Semantics, Discriminative model and Robustness.
Her Natural language study combines topics in areas such as Classifier and Transcription.
Her most cited work include:
- Prosody-based automatic segmentation of speech into sentences and topics (382 citations)
- Using recurrent neural networks for slot filling in spoken language understanding (326 citations)
- Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM. (271 citations)
What are the main themes of her work throughout her whole career to date?
Her main research concerns Artificial intelligence, Natural language processing, Speech recognition, Spoken language and Natural language.
Her Artificial intelligence research incorporates themes from Context and Dialog box.
She interconnects Conversation and Human–computer interaction in the investigation of issues within Dialog box.
Her Natural language processing study combines topics from a wide range of disciplines, such as Domain, Dialog system, Set and Information retrieval.
Her studies deal with areas such as Boosting and Segmentation as well as Speech recognition.
Her studies in Spoken language integrate themes in fields like Conditional random field, Classifier, Word, Deep learning and Discriminative model.
She most often published in these fields:
- Artificial intelligence (73.52%)
- Natural language processing (64.79%)
- Speech recognition (30.42%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (73.52%)
- Natural language processing (64.79%)
- Dialog box (13.24%)
In recent papers she was focusing on the following fields of study:
Her primary scientific interests are in Artificial intelligence, Natural language processing, Dialog box, Human–computer interaction and Domain.
Her Artificial intelligence study incorporates themes from Machine learning, State and Reading comprehension.
Her Natural language processing research integrates issues from Ontology and Context.
Dilek Hakkani-Tur has included themes like Natural language generation, Conversation and Open domain in her Dialog box study.
Her Human–computer interaction research incorporates elements of Task oriented, Natural language and Selection.
Her work deals with themes such as Recurrent neural network, Speech recognition, Encoding and Spoken language, which intersect with Word.
Between 2018 and 2021, her most popular works were:
- MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines (64 citations)
- Dialog State Tracking: A Neural Reading Comprehension Approach. (56 citations)
- HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking (34 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
Her scientific interests lie mostly in Artificial intelligence, Natural language processing, State, Human–computer interaction and Dialog box.
Specifically, her work in Artificial intelligence is concerned with the study of Training set.
Dilek Hakkani-Tur mostly deals with Automatic summarization in her studies of Natural language processing.
Her Human–computer interaction research is multidisciplinary, incorporating elements of Domain, Task oriented, Dialog system and Reinforcement learning.
Her Dialog box study which covers Conversation that intersects with SIGNAL, Relevance and Chatbot.
Her study in Machine learning is interdisciplinary in nature, drawing from both Tracking and Set.
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.
