Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model.
Lingfeng ShenHaiyun JiangLemao LiuShuming ShiPublished in: RepL4NLP@ACL (2023)
Keyphrases
- language model
- pre trained
- probabilistic model
- language modeling
- context sensitive
- n gram
- speech recognition
- dependency structure
- information retrieval
- training data
- document retrieval
- query expansion
- retrieval model
- query terms
- sentence retrieval
- mixture model
- generative model
- language modelling
- test collection
- natural language
- training examples
- uncertain data
- smoothing methods
- bayesian networks
- part of speech
- relevance model
- control signals
- divergence from randomness
- ad hoc information retrieval
- sentence level
- vector space
- decision trees
- unsupervised learning
- machine learning