V-SBERT: A Mixture Model for Closed-Domain Question-Answering Systems Based on Natural Language Processing and Deep Learning.
Yuan ZhuangBoyan LiuXiaotao LinCanhao XuPublished in: DSIT (2023)
Keyphrases
- mixture model
- deep learning
- unsupervised learning
- question answering systems
- natural language processing
- question answering
- machine learning
- em algorithm
- gaussian mixture model
- probabilistic model
- natural language
- model selection
- information extraction
- expectation maximization
- generative model
- language model
- semantic relations
- maximum likelihood
- domain specific
- feature selection
- named entities
- weakly supervised
- artificial intelligence
- information retrieval
- text mining
- supervised learning
- pairwise
- training data
- document retrieval