What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
His main research concerns Artificial intelligence, Information retrieval, Natural language processing, Automatic summarization and Multi-document summarization.
His Adversarial system study, which is part of a larger body of work in Artificial intelligence, is frequently linked to Happiness, bridging the gap between disciplines.
His Information retrieval research incorporates themes from Graph, Data mining, Cluster analysis, Ranking and Component.
His Natural language processing study frequently links to other fields, such as Leverage.
His Automatic summarization research incorporates elements of Sentence and Graph based.
His research integrates issues of Natural language generation, Word and Greedy algorithm in his study of Multi-document summarization.
His most cited work include:
- Co-Training for Cross-Lingual Sentiment Classification (384 citations)
- Single document keyphrase extraction using neighborhood knowledge (295 citations)
- Multi-document summarization using cluster-based link analysis (254 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Artificial intelligence, Natural language processing, Information retrieval, Automatic summarization and Sentence.
His Artificial intelligence study incorporates themes from Machine learning and Pattern recognition.
His work on Parsing, Cross lingual and Paraphrase as part of general Natural language processing research is frequently linked to Quality, bridging the gap between disciplines.
As part of the same scientific family, he usually focuses on Information retrieval, concentrating on Ranking and intersecting with Similitude.
His study in Automatic summarization is interdisciplinary in nature, drawing from both Graph, Data mining and Leverage.
In Data mining, Xiaojun Wan works on issues like Similarity, which are connected to Semantic similarity, Query expansion and Optimal matching.
He most often published in these fields:
- Artificial intelligence (53.98%)
- Natural language processing (42.92%)
- Information retrieval (35.84%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (53.98%)
- Natural language processing (42.92%)
- Automatic summarization (27.88%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Natural language processing, Automatic summarization, Transformer and Parsing.
His study ties his expertise on Machine learning together with the subject of Artificial intelligence.
His Natural language processing research is multidisciplinary, incorporating perspectives in Set, Word, Utterance and Pun.
Automatic summarization is a component of his Multi-document summarization and Document summarization studies.
His Transformer study integrates concerns from other disciplines, such as Autoencoder, Theoretical computer science, Text generation and Machine translation.
The study incorporates disciplines such as Context and Vocabulary in addition to Information retrieval.
Between 2017 and 2021, his most popular works were:
- SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks (93 citations)
- A Neural Approach to Pun Generation (28 citations)
- T-CVAE: transformer-based conditioned variational autoencoder for story completion (24 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
Xiaojun Wan focuses on Artificial intelligence, Natural language processing, Transformer, Automatic summarization and Benchmark.
Much of his study explores Artificial intelligence relationship to Machine learning.
His Natural language processing study combines topics from a wide range of disciplines, such as Word, Grammar and Readability.
Particularly relevant to Multi-document summarization is his body of work in Automatic summarization.
His Sentence research is multidisciplinary, incorporating elements of Granularity and Leverage.
The Domain study combines topics in areas such as Sentiment analysis, Embedding and Information retrieval.
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.
