What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Natural language processing
- Programming language
Gokhan Tur mainly investigates Artificial intelligence, Natural language processing, Spoken language, Speech recognition and Natural language.
Artificial intelligence is frequently linked to Machine learning in his study.
His Natural language processing study incorporates themes from Segmentation and Utterance.
His work deals with themes such as Recurrent neural network, Conditional random field, Semantics, Feature extraction and Discriminative model, which intersect with Spoken language.
His work carried out in the field of Speech recognition brings together such families of science as Sentence and Information extraction.
His Natural language research incorporates elements of Classifier, Spoken dialog systems, Semantic role labeling and Speech processing.
His most cited work include:
- Prosody-based automatic segmentation of speech into sentences and topics (382 citations)
- Spoken Language Understanding: Systems for Extracting Semantic Information from Speech (333 citations)
- Using recurrent neural networks for slot filling in spoken language understanding (326 citations)
What are the main themes of his work throughout his whole career to date?
Gokhan Tur spends much of his time researching Artificial intelligence, Natural language processing, Spoken language, Speech recognition and Natural language.
Gokhan Tur interconnects Machine learning and Information retrieval in the investigation of issues within Artificial intelligence.
Gokhan Tur has included themes like Domain, Utterance and Set in his Natural language processing study.
His research investigates the link between Spoken language and topics such as Web search query that cross with problems in Query expansion.
His research on Speech recognition also deals with topics like
- Discriminative model which intersects with area such as Feature extraction,
- Segmentation which is related to area like Statistical model.
In his research on the topic of Natural language, Reinforcement learning is strongly related with Human–computer interaction.
He most often published in these fields:
- Artificial intelligence (75.33%)
- Natural language processing (67.40%)
- Spoken language (32.60%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (75.33%)
- Human–computer interaction (9.69%)
- Natural language processing (67.40%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Human–computer interaction, Natural language processing, Artificial neural network and Parsing.
His study ties his expertise on Component together with the subject of Artificial intelligence.
His Human–computer interaction research incorporates themes from Pipeline, Dialog system, Natural language and Reinforcement learning.
His research in Natural language processing is mostly focused on Language model.
His studies deal with areas such as End-to-end principle, Speech recognition, Benchmark, Feature extraction and Discriminative model as well as Artificial neural network.
His Parsing research also works with subjects such as
- Process, Conjunction and Phrase most often made with reference to Encoding,
- Recurrent neural network, which have a strong connection to Spoken language.
Between 2016 and 2021, his most popular works were:
- Building a Conversational Agent Overnight with Dialogue Self-Play (100 citations)
- Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning (74 citations)
- Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems (73 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Machine learning
His primary scientific interests are in Artificial intelligence, Human–computer interaction, Parsing, Dialog system and Reinforcement learning.
Gokhan Tur studies Deep learning which is a part of Artificial intelligence.
His Parsing study is concerned with Natural language processing in general.
His Natural language processing research is multidisciplinary, relying on both Context and Encoding.
In his research, Bootstrapping is intimately related to Crowdsourcing, which falls under the overarching field of Dialog system.
His Reinforcement learning research includes elements of Task oriented, End-to-end principle, Conversation, Interactive Learning and Pipeline.
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.
