Vision Enhanced Generative Pre-trained Language Model for Multimodal Sentence Summarization.
Liqiang JingYiren LiJunhao XuYongcan YuPei ShenXuemeng SongPublished in: Mach. Intell. Res. (2023)
Keyphrases
- language model
- pre trained
- text summarization
- language modeling
- n gram
- query expansion
- dependency structure
- document retrieval
- training data
- probabilistic model
- generative model
- information retrieval
- speech recognition
- retrieval model
- training examples
- part of speech
- natural language
- test collection
- control signals
- ad hoc information retrieval
- computer vision
- query terms
- mixture model
- multi modal
- multi document summarization
- sentence level
- language modeling framework
- translation model
- smoothing methods
- natural language processing
- audio visual
- unsupervised learning
- pseudo relevance feedback
- small number
- training set