Clustering Contextualized Representations of Text for Unsupervised Syntax Induction.
Vikram GuptaHaoyue ShiKevin GimpelMrinmaya SachanPublished in: CoRR (2020)
Keyphrases
- unsupervised learning
- automatically discovering
- clustering algorithm
- k means
- text clustering
- unsupervised manner
- lexical semantics
- unsupervised classification
- text segmentation
- clustering method
- semi supervised
- syntactic analysis
- unsupervised clustering
- short text
- data clustering
- supervised classification
- information bottleneck
- cluster validation
- unsupervised feature selection
- text mining
- categorical data
- completely unsupervised
- document clustering
- self organizing maps
- inductive learning
- cluster analysis
- dimensionality reduction
- hierarchical clustering
- supervised learning
- keywords
- data representations
- information retrieval
- semantic representations
- text retrieval
- syntactic categories
- agglomerative clustering
- inductive logic programming
- grammar induction
- database
- high dimensional data
- data points
- machine learning
- data mining