Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings
arXiv:2011.01565
Abstract
Social media produces large amounts of contents every day. To help users quickly capture what they need, keyphrase prediction is receiving a growing attention. Nevertheless, most prior efforts focus on text modeling, largely ignoring the rich features embedded in the matching images. In this work, we explore the joint effects of texts and images in predicting the keyphrases for a multimedia post. To better align social media style texts and images, we propose: (1) a novel Multi-Modality Multi-Head Attention (M3H-Att) to capture the intricate cross-media interactions; (2) image wordings, in forms of optical characters and image attributes, to bridge the two modalities. Moreover, we design a unified framework to leverage the outputs of keyphrase classification and generation and couple their advantages. Extensive experiments on a large-scale dataset newly collected from Twitter show that our model significantly outperforms the previous state of the art based on traditional attention networks. Further analyses show that our multi-head attention is able to attend information from various aspects and boost classification or generation in diverse scenarios.
arXiv commentEMNLP 2020 (14 pages)
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Neural Machine Translation by Jointly Learning to Align and Translate
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- VD-BERT: A Unified Vision and Dialog Transformer with BERT
- Microblog Hashtag Generation via Encoding Conversation Contexts