Recent development of generative pretrained language models has been proven very successful on a widerange of NLP tasks, such as text classification, question answering, textual entailment and so on.In thiswork, we present a two-phase encoder decoder architecture based on Bidirectional EncodingRepresentation from Transformers(BERT) for extractive summarization task. We evaluated our model byboth automatic metrics and human annotators, and demonstrated that the architecture achieves the state-of-the-art comparable result on large scale corpus - CNN/Daily Mail 1 . As the best of our knowledge, thisis the first work that applies BERT based architecture to a text summarization task and achieved the state-of-the-art comparable result.
展开▼