Multi-Media Multi-Lingual Information Extraction, Summarization and Transfer

Information Extraction (IE) and Summarization are fundamental tasks in Natural Language Processing (NLP) which can provide input to downstream applications such as search, recommendation, question answering, and dialogue generation. Most of the research on IE and Summarization focuses on text only. However with the popularity of mobile devices, the data in daily life is becoming more and more multimodal. People share millions of multimodal posts in social media sites everyday, containing both texts and images. Often those short and noisy text in social media can only be understood if combined with visual context.