What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Word, Theoretical computer science and Recurrent neural network.
His research investigates the connection between Artificial intelligence and topics such as Machine learning that intersect with issues in Adversarial system.
His work deals with themes such as Context, Training set, Artificial neural network, Information retrieval and Test set, which intersect with Natural language processing.
His study in the field of Word embedding is also linked to topics like Gender bias.
In his research on the topic of Theoretical computer science, Parsing, Parser combinator and Range is strongly related with Algorithm.
As a part of the same scientific study, Yoav Goldberg usually deals with the Recurrent neural network, concentrating on Deep learning and frequently concerns with Nervous system network models, Types of artificial neural networks, Neural network software, Cellular neural network and Time delay neural network.
His most cited work include:
- Neural Word Embedding as Implicit Matrix Factorization (1213 citations)
- Improving Distributional Similarity with Lessons Learned from Word Embeddings (914 citations)
- word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. (839 citations)
What are the main themes of his work throughout his whole career to date?
Yoav Goldberg mainly focuses on Artificial intelligence, Natural language processing, Parsing, Word and Machine learning.
Many of his studies involve connections with topics such as Pattern recognition and Artificial intelligence.
His Natural language processing research incorporates themes from Context, Speech recognition and Hebrew.
The Parsing study which covers Algorithm that intersects with Theoretical computer science.
His Word research is multidisciplinary, incorporating elements of Semantics and Representation.
His Language model research is multidisciplinary, relying on both Artificial neural network, Focus and Domain.
He most often published in these fields:
- Artificial intelligence (81.78%)
- Natural language processing (62.15%)
- Parsing (25.70%)
What were the highlights of his more recent work (between 2020-2021)?
- Artificial intelligence (81.78%)
- Natural language processing (62.15%)
- Process (11.68%)
In recent papers he was focusing on the following fields of study:
Yoav Goldberg mostly deals with Artificial intelligence, Natural language processing, Process, Natural language and Language model.
His work in the fields of Embedding overlaps with other areas such as Structure.
His biological study spans a wide range of topics, including Historical linguistics, Sign language, Sound change and Relation.
His study in Natural language is interdisciplinary in nature, drawing from both Distress, Association, Lexicon, Semantics and Multilevel model.
Yoav Goldberg interconnects Equivalence, SIGNAL, Cognitive science and Meaning in the investigation of issues within Language model.
His Space research is multidisciplinary, incorporating perspectives in Value, Event, Contrast and Representation.
Between 2020 and 2021, his most popular works were:
- Amnesic Probing: Behavioral Explanation With Amnesic Counterfactuals (8 citations)
- Measuring and Improving Consistency in Pretrained Language Models (5 citations)
- Contrastive Explanations for Model Interpretability. (3 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
Yoav Goldberg mainly investigates Attribution, Property, Point, Natural language processing and Artificial intelligence.
Attribution is connected with Process, Causal chain, Interpretation, Causality and Event in his research.
His research in Property intersects with topics in Language model and Consistency.
Point is connected with Scrutiny, Intervention, Alternative methods, Representation and Cognitive psychology in his study.
His Natural language processing study combines topics from a wide range of disciplines, such as Contrast, Space, Representation, Interpretability and Value.
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.
