What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- World Wide Web
His primary areas of investigation include Information retrieval, Artificial intelligence, Natural language processing, Ranking and Data mining.
His Information retrieval study combines topics from a wide range of disciplines, such as Web resource and World Wide Web.
When carried out as part of a general Artificial intelligence research project, his work on Paraphrase is frequently linked to work in Weighting, therefore connecting diverse disciplines of study.
The study incorporates disciplines such as Discourse relation and Segmentation in addition to Natural language processing.
His Ranking research focuses on Ranking and how it connects with Relation, Mutual information and Question answering.
His Data mining study integrates concerns from other disciplines, such as Feature, Cluster analysis, Fuzzy clustering, Query expansion and Component.
His most cited work include:
- Fast Matrix Factorization for Online Recommendation with Implicit Feedback (507 citations)
- SemEval-2010 Task 5 : Automatic Keyphrase Extraction from Scientific Articles (264 citations)
- ParsCit: an Open-source CRF Reference String Parsing Package (262 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Information retrieval, Artificial intelligence, Natural language processing, World Wide Web and Digital library.
His work deals with themes such as Metadata and Web page, which intersect with Information retrieval.
His Artificial intelligence study combines topics in areas such as Context and Machine learning.
His research in Natural language processing intersects with topics in Speech recognition, Word and Vocabulary.
His study ties his expertise on User interface together with the subject of World Wide Web.
His Multi-document summarization study in the realm of Automatic summarization interacts with subjects such as Information technology.
He most often published in these fields:
- Information retrieval (40.16%)
- Artificial intelligence (36.22%)
- Natural language processing (29.92%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (36.22%)
- Information retrieval (40.16%)
- Natural language processing (29.92%)
In recent papers he was focusing on the following fields of study:
Min-Yen Kan mostly deals with Artificial intelligence, Information retrieval, Natural language processing, Question generation and World Wide Web.
His Artificial intelligence research focuses on Variation and how it relates to Embedding.
When carried out as part of a general Information retrieval research project, his work on Recommender system is frequently linked to work in Modal, therefore connecting diverse disciplines of study.
The various areas that Min-Yen Kan examines in his Natural language processing study include Dependency, Context, Comprehension and Inflection.
In his work, Relevance and Data science is strongly intertwined with Forcing, which is a subfield of Question generation.
Min-Yen Kan interconnects Question answering, Thread and Anchoring in the investigation of issues within World Wide Web.
Between 2018 and 2021, his most popular works were:
- Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems (46 citations)
- Recent Advances in Neural Question Generation. (35 citations)
- It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations. (26 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- World Wide Web
Information retrieval, Natural language processing, Artificial intelligence, Question generation and African American Vernacular English are his primary areas of study.
His Information retrieval research is multidisciplinary, relying on both Schema and SQL.
Particularly relevant to Parsing is his body of work in Natural language processing.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Style and Dialog box.
His Question generation research is multidisciplinary, incorporating perspectives in Variety, Cognitive science and Human intelligence.
His studies in Recommender system integrate themes in fields like Reflection and Conversation.
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.
