Sarcasm is important to sentiment analysis on social media. Sarcasm Target Identification (STI) deserves further study to understand sarcasm in depth. However, text lacking context or missing sarcasm target makes target identification very difficult. In this paper, we introduce multimodality to STI and present Multimodal Sarcasm Target Identification (MSTI) task. We propose a novel multi-scale cross-modality model that can simultaneously perform textual target labeling and visual target detection. In the model, we extract multi-scale visual features to enrich spatial information for different sized visual sarcasm targets. We design a set of convolution networks to unify multi-scale visual features with textual features for cross-modal attention learning, and correspondingly a set of transposed convolution networks to restore multi-scale visual information. The results show that visual clues can improve the performance of TSTI by a large margin, and VSTI achieves good accuracy.

Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. Visual clues unrelated to the text would incur uncertain or even negative effects for multimodal model learning. In this paper, we propose a novel pre-trained multimodal model based on Relationship Inference and Visual Attention (RIVA) for tweets. The RIVA model controls the attention-based visual clues with a gate regarding the role of image to the semantics of text. We use a teacher-student semi-supervised paradigm to leverage a large unlabeled multimodal tweet corpus with a labeled data set for text-image relation classification. 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.