Knowledge-aware document summarization: A survey of knowledge, embedding methods and architectures

Knowledge-aware methods have boosted a range of natural language processing applications over the last decades. With gathered momentum, knowledge recently has been pumped into enormous attention in document summarization, one applications. Previous works reported that knowledge-embedded summarizers excel at generating superior digests, especially terms informativeness, coherence, and fact consistency. This paper pursues to present first systematic survey for state-of-the-art methodologies embed summarizers. Particularly, we propose novel taxonomies recapitulate embeddings under summarization view. We further explore how are generated embedding learning architectures models, deep models. At last, discuss challenges this topic future directions.