Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization.
Tiezheng YuWenliang DaiZihan LiuPascale FungPublished in: EMNLP (1) (2021)
Keyphrases
- language model
- vision guided
- pre trained
- mobile robot navigation
- language modeling
- training data
- natural scenes
- n gram
- probabilistic model
- generative model
- training examples
- speech recognition
- information retrieval
- query expansion
- multi modal
- mobile robot
- language modeling framework
- smoothing methods
- control signals
- natural images
- active learning
- audio visual
- relevance model
- pairwise
- multimedia
- machine learning