What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Natural language processing, Component and Artificial neural network.
Her Artificial intelligence study incorporates themes from Speech recognition, Task and State.
Her Machine learning research is multidisciplinary, relying on both Dialogue management and Dialog box.
Milica Gasic combines subjects such as Set and Reinforcement learning with her study of Dialogue management.
Her Natural language processing study combines topics in areas such as Generator, Dynamic Bayesian network, Word and Graphical model.
Her work in Artificial neural network covers topics such as End-to-end principle which are related to areas like Statistical learning and Human–computer interaction.
Her most cited work include:
- POMDP-Based Statistical Spoken Dialog Systems: A Review (604 citations)
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems (512 citations)
- The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management (471 citations)
What are the main themes of her work throughout her whole career to date?
Milica Gasic mainly focuses on Artificial intelligence, Reinforcement learning, Machine learning, Natural language processing and Task.
Her Artificial intelligence research includes elements of Speech recognition and State.
Her research in Reinforcement learning intersects with topics in Artificial neural network, Dialogue management, Human–computer interaction, Function and Set.
Her research in the fields of Recurrent neural network and Active learning overlaps with other disciplines such as Sample.
Her Natural language processing research focuses on Word and how it relates to Semantic similarity.
The concepts of her Task study are interwoven with issues in Context and Representation.
She most often published in these fields:
- Artificial intelligence (72.44%)
- Reinforcement learning (36.22%)
- Machine learning (34.65%)
What were the highlights of her more recent work (between 2017-2020)?
- Artificial intelligence (72.44%)
- Reinforcement learning (36.22%)
- Task (20.47%)
In recent papers she was focusing on the following fields of study:
Her primary areas of investigation include Artificial intelligence, Reinforcement learning, Task, State and Human–computer interaction.
Her Artificial intelligence research includes themes of Conversation and Natural language processing.
Machine learning covers she research in Reinforcement learning.
Her work deals with themes such as Sentence and Context, which intersect with Task.
Her study in State is interdisciplinary in nature, drawing from both Tracking and Dialog box.
Her Human–computer interaction study incorporates themes from Corpus based, Relation and Natural language.
Between 2017 and 2020, her most popular works were:
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (247 citations)
- Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing (76 citations)
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (39 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
Milica Gasic mainly investigates Reinforcement learning, Artificial intelligence, Task, Human–computer interaction and Ontology.
Her research in Artificial intelligence intersects with topics in Machine learning, Task analysis, Function and Natural language processing.
Her research investigates the connection with Task analysis and areas like Artificial neural network which intersect with concerns in Set, Deep learning and Dialogue management.
Her studies deal with areas such as Active learning, Recurrent neural network and Dimension as well as Function.
Her Task research is multidisciplinary, relying on both Context, Corpus based, Data mining and Natural language.
Her Ontology study integrates concerns from other disciplines, such as Knowledge sharing and Semantic similarity.
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.
