Search Results for author:
Found 3 papers, 2 papers with code
Multimodal Sarcasm Target Identification in Tweets
Sarcasm is important to sentiment analysis on social media.
RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER
We integrate soft or hard gates to select visual clues and propose a multitask algorithm to train on the MNER datasets.
Ranked #5 on
Multi-modal Named Entity Recognition
on Twitter-15
Multi-modal Named Entity Recognition
named-entity-recognition
+2
RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER
In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.
