A Large-Scale Chinese Multimodal NER Dataset with Speech Clues.
Dianbo SuiZhengkun TianYubo ChenKang LiuJun ZhaoPublished in: ACL/IJCNLP (1) (2021)
Keyphrases
- text summarization
- named entity recognition
- audio visual
- speech recognition
- maximum entropy
- multimodal interfaces
- information extraction
- multi modal
- english text
- real world
- natural language processing
- conditional random fields
- benchmark datasets
- speech synthesis
- multi stream
- speech signal
- real life
- artificial intelligence
- automatic speech recognition
- small scale
- named entities
- web scale
- spoken language
- million images
- text to speech
- synthetic datasets
- multimodal interaction
- hidden markov models
- multimodal data
- story segmentation