Enhancing Coherence of Extractive Summarization with Multitask Learning
This work addresses coherence issues in extractive summarization for NLP applications, representing an incremental improvement over existing methods.
The study tackled the problem of low coherence in extractive summarization by proposing a multitask learning architecture with a coherent discriminator, resulting in a significant improvement in the proportion of consecutive sentences in summaries while preserving other automatic metrics like Rouge scores and BertScores.
This study proposes a multitask learning architecture for extractive summarization with coherence boosting. The architecture contains an extractive summarizer and coherent discriminator module. The coherent discriminator is trained online on the sentence vectors of the augmented textual input, thus improving its general ability of judging whether the input sentences are coherent. Meanwhile, we maximize the coherent scores from the coherent discriminator by updating the parameters of the summarizer. To make the extractive sentences trainable in a differentiable manner, we introduce two strategies, including pre-trained converting model (model-based) and converting matrix (MAT-based) that merge sentence representations. Experiments show that our proposed method significantly improves the proportion of consecutive sentences in the extracted summaries based on their positions in the original article (i.e., automatic sentence-level coherence metric), while the goodness in terms of other automatic metrics (i.e., Rouge scores and BertScores) are preserved. Human evaluation also evidences the improvement of coherence and consistency of the extracted summaries given by our method.