BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization
This work addresses data efficiency in summarization for NLP applications, representing an incremental improvement.
The paper tackles the problem of limited and noisy training data in abstractive summarization by proposing the BiSET model, which uses templates to select key information from source articles, achieving a new state-of-the-art performance on a standard dataset.
The success of neural summarization models stems from the meticulous encodings of source articles. To overcome the impediments of limited and sometimes noisy training data, one promising direction is to make better use of the available training data by applying filters during summarization. In this paper, we propose a novel Bi-directional Selective Encoding with Template (BiSET) model, which leverages template discovered from training data to softly select key information from each source article to guide its summarization process. Extensive experiments on a standard summarization dataset were conducted and the results show that the template-equipped BiSET model manages to improve the summarization performance significantly with a new state of the art.