What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Natural language processing
Wanxiang Che mainly investigates Artificial intelligence, Natural language processing, Parsing, Word and Dependency grammar.
His research integrates issues of Named-entity recognition and Pattern recognition in his study of Artificial intelligence.
His study in the field of Sentence is also linked to topics like Encoder.
His study connects Discriminative model and Parsing.
His study in Word is interdisciplinary in nature, drawing from both Relation and Semantic similarity.
His Dependency grammar research integrates issues from S-attributed grammar, Graph and Syntactic predicate.
His most cited work include:
- LTP: A Chinese Language Technology Platform (321 citations)
- Learning Semantic Hierarchies via Word Embeddings (208 citations)
- Cross-lingual Dependency Parsing Based on Distributed Representations (161 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Natural language processing, Parsing, Word and Dependency grammar.
His Artificial intelligence research incorporates elements of Machine learning, Named-entity recognition and Pattern recognition.
His Natural language processing research includes themes of Margin, Context and Speech recognition.
His research in Parsing intersects with topics in Annotation and Graph.
Wanxiang Che interconnects Pipeline, Semantic role labeling and Focus in the investigation of issues within Word.
Wanxiang Che has researched Dependency grammar in several fields, including Language model, Space and Syntactic predicate.
He most often published in these fields:
- Artificial intelligence (78.70%)
- Natural language processing (59.76%)
- Parsing (26.63%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (78.70%)
- Natural language processing (59.76%)
- Spoken language (7.69%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Natural language processing, Spoken language, Graph and Transformer.
His Artificial intelligence study which covers Machine learning that intersects with Language understanding.
Wanxiang Che works in the field of Natural language processing, namely Sentence.
His research investigates the connection with Graph and areas like Utterance which intersect with concerns in Graph traversal.
His Transformer research is multidisciplinary, relying on both F1 score, Computer engineering and Task.
In his study, Parsing is inextricably linked to Pattern recognition, which falls within the broad field of Projection.
Between 2019 and 2021, his most popular works were:
- Revisiting Pre-Trained Models for Chinese Natural Language Processing (29 citations)
- Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (21 citations)
- DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification (16 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Natural language processing
Wanxiang Che focuses on Artificial intelligence, Natural language processing, Conversation, Human–computer interaction and Graph.
His Artificial intelligence study frequently intersects with other fields, such as Machine learning.
He mostly deals with Parsing in his studies of Natural language processing.
His Conversation study integrates concerns from other disciplines, such as Consistency, Coherence and Knowledge graph.
His biological study spans a wide range of topics, including Context and Reinforcement learning.
His Graph research includes elements of Machine reading, Comprehension and Utterance.
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.
