What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Natural language processing
- Programming language
The scientist’s investigation covers issues in Artificial intelligence, Natural language processing, Automatic summarization, Parsing and Meaning.
Her Artificial intelligence research incorporates themes from Process and State.
Mirella Lapata interconnects Machine learning and Information retrieval in the investigation of issues within Natural language processing.
The various areas that Mirella Lapata examines in her Machine learning study include Graph, Connectivity, Graph, Range and Semantics.
Mirella Lapata has researched Automatic summarization in several fields, including Algorithm, Optimization problem and Theoretical computer science.
Her Parsing research is multidisciplinary, relying on both Chunking, Chunking, Head-driven phrase structure grammar and Identification.
Her most cited work include:
- Composition in distributional models of semantics. (781 citations)
- Vector-based Models of Semantic Composition (623 citations)
- Dependency-Based Construction of Semantic Space Models (539 citations)
What are the main themes of her work throughout her whole career to date?
Her primary scientific interests are in Artificial intelligence, Natural language processing, Automatic summarization, Parsing and Sentence.
Her Artificial intelligence research includes themes of Machine learning, Information retrieval and Selection.
Her Natural language processing research integrates issues from Context, Word and Meaning.
Her research in the fields of Multi-document summarization overlaps with other disciplines such as Encoder.
Within one scientific family, Mirella Lapata focuses on topics pertaining to Dependency under Parsing, and may sometimes address concerns connected to Syntax.
Her research investigates the connection between Sentence and topics such as Artificial neural network that intersect with problems in State.
She most often published in these fields:
- Artificial intelligence (74.26%)
- Natural language processing (64.36%)
- Automatic summarization (18.81%)
What were the highlights of her more recent work (between 2018-2021)?
- Artificial intelligence (74.26%)
- Natural language processing (64.36%)
- Automatic summarization (18.81%)
In recent papers she was focusing on the following fields of study:
Artificial intelligence, Natural language processing, Automatic summarization, Transformer and Parsing are her primary areas of study.
Her work in Artificial intelligence tackles topics such as Machine learning which are related to areas like Text generation.
The Natural language processing study combines topics in areas such as Narrative structure and German.
Her Automatic summarization research is multidisciplinary, incorporating elements of Language model, Salient and Training set.
As part of one scientific family, Mirella Lapata deals mainly with the area of Transformer, narrowing it down to issues related to the Benchmark, and often Cluster analysis, Interpretation and Space.
The concepts of her Parsing study are interwoven with issues in Recurrent neural network, Theoretical computer science, Representation, Utterance and Semantic role labeling.
Between 2018 and 2021, her most popular works were:
- Text Summarization with Pretrained Encoders (280 citations)
- Data-to-Text Generation with Content Selection and Planning (111 citations)
- Text Generation from Knowledge Graphs with Graph Transformers (103 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Natural language processing
- Programming language
Her scientific interests lie mostly in Artificial intelligence, Natural language processing, Automatic summarization, Artificial neural network and Sentence.
In her works, Mirella Lapata conducts interdisciplinary research on Artificial intelligence and Content.
Her Parsing study in the realm of Natural language processing connects with subjects such as Screenwriting.
Her Automatic summarization research also works with subjects such as
- Transformer that connect with fields like Multi-document summarization and Language model,
- Salient and related Personalization, Set, State, Information retrieval and Noise.
Her Artificial neural network study combines topics in areas such as Annotation, Feature learning, Leverage and Text generation.
Her work carried out in the field of Sentence brings together such families of science as Natural language understanding, Word, Inference, n-gram and Representation.
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.
