Named Entity Recognition (NER) in social media posts is challenging since texts are usually short and contexts are lacking. Most recent works show that visual information can boost the NER performance since images can provide complementary contextual information for texts. However, the image-level features ignore the mapping relations between fine-grained visual objects and textual entities, which results in error detection in entities with different types. To better exploit visual and textual information in NER, we propose an adversarial gated bilinear attention neural network (AGBAN). The model jointly extracts entity-related features from both visual objects and texts, and leverages an adversarial training to map two different representations into a shared representation. As a result, domain information contained in an image can be transferred and applied for extracting named entities in the text associated with the image. Experimental results on Tweets dataset demonstrate that our model outperforms the state-of-the-art methods. Moreover, we systematically evaluate the effectiveness of the proposed gated bilinear attention network in capturing the interactions of mutimodal features visual objects and textual words. Our results indicate that the adversarial training can effectively exploit commonalities across heterogeneous data sources, which leads to improved performance in NER when compared to models purely exploiting text data or combining the image-level visual features.

Changmeng Zheng, Yi Cai, Jingyun Xu, Ho-fung Leung, Guandong Xu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This paper is the first to propose jointly performing MNER and MRE as a joint multimodal entity-relation extraction (JMERE) task . Besides, the current MNER and MRE models only consider aligning the visual objects with textual entities in visual and textual graphs but ignore the entity-entity relationships and object-object relationships. To address the above challenges, we propose an edge-enhanced graph alignment network and a word-pair relation tagging (EEGA) for the JMERE task. Specifically, we first design a word-pair relation tagging to exploit the bidirectional interaction between MNER and MRE and avoid error propagation. Then, we propose an edge-enhanced graph alignment network to enhance the JMERE task by aligning nodes and edges in the cross-graph. Compared with previous methods, the proposed method can leverage the edge information to auxiliary alignment between objects and entities and find the correlations between entity-entity relationships and object-object relationships. Experiments are conducted to show the effectiveness of our model.

The task of image difference captioning aims at locating changed objects in similar image pairs and describing the difference with natural language. The key challenges of this task are to comprehend the context of image pairs sufficiently and locate the changed objects accurately in the presence of viewpoint change. Previous studies focus on pixel-level image features, neglecting rich explicit features of objects in an image pair which are beneficial to generate a fine-grained difference caption. Additionally, existing generative models suffer from accurately locate the differences in the interference of viewpoint change. To address these issues, we propose an Instance-Level Fine-Grained Difference Captioning (IFDC) model, which consists of a fine-grained feature extraction module, a multi-round feature fusion module, a similarity-based difference finding module, and a difference captioning module. To describe the changed objects comprehensively, we extract the fine-grained features, i.e., visual features, semantic features, and positional features at instance-level, as the objects’ representation. To enhance the model’s immunity to viewpoint change, we design a similarity-based difference finding module to locate the changed objects accurately. Extensive experiments show that our IFDC model achieves comparable performance with the state-of-the-art models on the datasets of CLEVR-Change and Spot-the-Diff, thus verifying the effectiveness of our proposed model. Our source code is available at https://github.com/VISLANG-Lab/IFDC .