What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Information retrieval
Dina Demner-Fushman spends much of her time researching Information retrieval, Artificial intelligence, Natural language processing, Question answering and Domain.
Her Information retrieval research includes themes of Modality and Image retrieval.
The various areas that Dina Demner-Fushman examines in her Artificial intelligence study include Terminology and Machine learning.
Her Natural language processing study integrates concerns from other disciplines, such as Vocabulary and R-CAST.
Her Question answering research integrates issues from Data science, Logical consequence, Biomedical text mining and Automatic summarization.
Her studies deal with areas such as Baseline, Complex question, Descriptive knowledge, Inference and Information seeking as well as Domain.
Her most cited work include:
- Methodological Review: What can natural language processing do for clinical decision support? (401 citations)
- Evaluation of PICO as a Knowledge Representation for Clinical Questions (329 citations)
- Frontiers of biomedical text mining: current progress (247 citations)
What are the main themes of her work throughout her whole career to date?
Her primary scientific interests are in Information retrieval, Artificial intelligence, Natural language processing, Question answering and Search engine indexing.
Her studies in Information retrieval integrate themes in fields like Image retrieval, Visual Word and Domain.
Her work in Artificial intelligence tackles topics such as Pattern recognition which are related to areas like Modality.
Her Natural language processing study combines topics from a wide range of disciplines, such as Annotation, Recall, Named-entity recognition and Ontology.
Her work deals with themes such as Data science and Automatic summarization, which intersect with Question answering.
Her Data science study incorporates themes from Information needs and Biomedical text mining.
She most often published in these fields:
- Information retrieval (45.86%)
- Artificial intelligence (40.98%)
- Natural language processing (25.94%)
What were the highlights of her more recent work (between 2017-2021)?
- Artificial intelligence (40.98%)
- Question answering (16.92%)
- Information retrieval (45.86%)
In recent papers she was focusing on the following fields of study:
Dina Demner-Fushman spends much of her time researching Artificial intelligence, Question answering, Information retrieval, Natural language processing and Automatic summarization.
Her Deep learning, Domain knowledge and Language model study, which is part of a larger body of work in Artificial intelligence, is frequently linked to Rank, bridging the gap between disciplines.
Her Question answering study combines topics in areas such as Domain, Inference, Natural language and Data science.
Her research ties Annotation and Information retrieval together.
Dina Demner-Fushman studies Natural language processing, namely Text mining.
In her research, Transformer, Shot, Realization and Selection is intimately related to Zero, which falls under the overarching field of Automatic summarization.
Between 2017 and 2021, her most popular works were:
- Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering (50 citations)
- TREC-COVID: rationale and structure of an information retrieval shared task for COVID-19. (47 citations)
- A question-entailment approach to question answering. (31 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Information retrieval
Dina Demner-Fushman mainly focuses on Question answering, Information retrieval, Artificial intelligence, Natural language and Inference.
Her Question answering research incorporates elements of Domain, Search engine indexing and Automatic summarization.
Many of her research projects under Information retrieval are closely connected to Track with Track, tying the diverse disciplines of science together.
Her biological study spans a wide range of topics, including Spelling, Error detection and correction and Natural language processing.
Her Natural language processing study integrates concerns from other disciplines, such as Ranking, Context and Word, Word2vec.
Her Inference study incorporates themes from Logical consequence, Deep learning and Data science.
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.
