Global Encoding For Abstractive Summarization · The Large Language Model Bible Contribute to LLM-Bible

Global Encoding For Abstractive Summarization

Lin Junyang, Sun Xu, Ma Shuming, Su Qi. Arxiv 2018

[Paper]    
Applications Tools

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information flow from the encoder to the decoder based on the global information of the source context. It consists of a convolutional gated unit to perform global encoding to improve the representations of the source-side information. Evaluations on the LCSTS and the English Gigaword both demonstrate that our model outperforms the baseline models, and the analysis shows that our model is capable of reducing repetition.

Similar Work