Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling
This work addresses summarization efficiency and quality for NLP applications, but it is incremental as it builds on existing methods like BERT and Transformers.
The authors tackled abstractive text summarization by conditioning Transformer models on BERT and using locality modeling, resulting in models that outperformed baselines in ROUGE scores on CNN/Daily Mail and SwissText datasets.
We explore to what extent knowledge about the pre-trained language model that is used is beneficial for the task of abstractive summarization. To this end, we experiment with conditioning the encoder and decoder of a Transformer-based neural model on the BERT language model. In addition, we propose a new method of BERT-windowing, which allows chunk-wise processing of texts longer than the BERT window size. We also explore how locality modelling, i.e., the explicit restriction of calculations to the local context, can affect the summarization ability of the Transformer. This is done by introducing 2-dimensional convolutional self-attention into the first layers of the encoder. The results of our models are compared to a baseline and the state-of-the-art models on the CNN/Daily Mail dataset. We additionally train our model on the SwissText dataset to demonstrate usability on German. Both models outperform the baseline in ROUGE scores on two datasets and show its superiority in a manual qualitative analysis.