What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
Shafiq Joty spends much of his time researching Artificial intelligence, Natural language processing, Machine learning, Deep learning and Word.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Margin, Speech recognition and Graph.
As part of the same scientific family, Shafiq Joty usually focuses on Margin, concentrating on Conditional random field and intersecting with Rhetorical question, Tree and Discourse analysis.
In general Natural language processing study, his work on Parsing often relates to the realm of Asynchronous communication, thereby connecting several areas of interest.
His work on AdaBoost, Activity recognition and Support vector machine is typically connected to Actigraphy and Wearable technology as part of general Machine learning study, connecting several disciplines of science.
His studies in Word integrate themes in fields like Feature engineering and Recurrent neural network.
His most cited work include:
- Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings (241 citations)
- Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models (173 citations)
- Codra: A novel discriminative framework for rhetorical analysis (133 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Natural language processing, Machine learning, Machine translation and Question answering.
His study explores the link between Artificial intelligence and topics such as Margin that cross with problems in Named-entity recognition.
His research in the fields of Parsing overlaps with other disciplines such as Tree kernel.
His biological study spans a wide range of topics, including Rhetorical Structure Theory, Time complexity and Discourse analysis.
Shafiq Joty combines subjects such as Language model, Training set, Adversarial system and Conditional random field with his study of Machine learning.
His Machine translation study integrates concerns from other disciplines, such as Translation and Benchmark.
He most often published in these fields:
- Artificial intelligence (71.12%)
- Natural language processing (42.78%)
- Machine learning (24.06%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (71.12%)
- Natural language processing (42.78%)
- Machine translation (19.25%)
In recent papers he was focusing on the following fields of study:
Shafiq Joty mostly deals with Artificial intelligence, Natural language processing, Machine translation, Machine learning and Language model.
Artificial intelligence is closely attributed to Named-entity recognition in his study.
His Natural language processing research incorporates elements of Context, Encoding, Inflection, Margin and Conversation.
His work in Margin tackles topics such as Word which are related to areas like Theoretical computer science.
His work on BLEU as part of his general Machine translation study is frequently connected to Coherence, Downstream and Diversification, thereby bridging the divide between different branches of science.
His Machine learning research is multidisciplinary, incorporating perspectives in Time complexity, Natural language generation and Automatic summarization.
Between 2019 and 2021, his most popular works were:
- It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations. (26 citations)
- GeDi: Generative Discriminator Guided Sequence Generation (19 citations)
- Tree-Structured Attention with Hierarchical Accumulation (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
Shafiq Joty mainly investigates Artificial intelligence, Natural language processing, Transformer, Margin and Dialog box.
The study incorporates disciplines such as Machine learning and Feature in addition to Artificial intelligence.
His Machine learning study combines topics in areas such as Time complexity and Parse tree.
His Natural language processing research includes elements of World Englishes, Encoding, Inflection, Vocabulary and Variation.
His work carried out in the field of Transformer brings together such families of science as Artificial neural network, Standard English, Singapore English, Linguistic discrimination and Morphology.
He has included themes like Theoretical computer science, Named-entity recognition and Cross lingual in his Margin study.
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.
