What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
Asli Celikyilmaz focuses on Artificial intelligence, Natural language processing, Reinforcement learning, Spoken language and Task completion.
His work in Neuro-fuzzy, Natural language, Fuzzy number, Defuzzification and Fuzzy classification is related to Artificial intelligence.
Asli Celikyilmaz has included themes like Visual reasoning and Benchmark in his Natural language study.
Asli Celikyilmaz studies Automatic summarization which is a part of Natural language processing.
His Spoken language research includes themes of Context, Speech recognition and Gesture.
His Task completion study combines topics from a wide range of disciplines, such as End-to-end principle and State.
His most cited work include:
- Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM. (271 citations)
- Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation (185 citations)
- Deep Communicating Agents for Abstractive Summarization (184 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Natural language processing, Reinforcement learning, Machine learning and Natural language.
He conducts interdisciplinary study in the fields of Artificial intelligence and Domain through his research.
His Natural language processing research incorporates elements of Context, Speech recognition, Utterance, Word and Web search query.
His Reinforcement learning study combines topics in areas such as Task completion and Human–computer interaction.
His Machine learning research incorporates themes from Fuzzy number, Neuro-fuzzy and Natural language understanding.
His Spoken language study incorporates themes from Topic model, Information retrieval, Deep learning and Bayesian inference.
He most often published in these fields:
- Artificial intelligence (81.12%)
- Natural language processing (50.35%)
- Reinforcement learning (17.48%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (81.12%)
- Natural language processing (50.35%)
- Automatic summarization (12.59%)
In recent papers he was focusing on the following fields of study:
Asli Celikyilmaz spends much of his time researching Artificial intelligence, Natural language processing, Automatic summarization, Reinforcement learning and Set.
The concepts of his Artificial intelligence study are interwoven with issues in Machine learning and Selection.
His work in the fields of Transformer and Relevance overlaps with other areas such as Working memory and Quality.
The study incorporates disciplines such as Supervised learning, Leverage and Closed captioning in addition to Natural language processing.
His work carried out in the field of Automatic summarization brings together such families of science as Sentence, Consistency and Data mining.
His research integrates issues of Robot and Human–computer interaction in his study of Reinforcement learning.
Between 2019 and 2021, his most popular works were:
- Evaluation of Text Generation: A Survey (30 citations)
- PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking (14 citations)
- Go Figure! A Meta Evaluation of Factuality in Summarization. (6 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
His primary areas of investigation include Artificial intelligence, Natural language processing, Automatic summarization, Key and Working memory.
His Artificial intelligence research is multidisciplinary, incorporating elements of Consistency and Plot, Narrative.
Asli Celikyilmaz has researched Natural language processing in several fields, including State and Task.
His Automatic summarization research includes elements of Natural language generation, Source text and Text generation.
He incorporates a variety of subjects into his writings, including Key, Component, Multi domain, Benchmark, Information retrieval and Set.
Machine learning and Transformer are fields of study that intersect with his Working memory research.
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.
