Sentence-level extractive text summarization is substantially a node classification task of network mining, adhering to the informative components and concise representations. There are lots of redundant phrases between extracted sentences, but it is difficult to model them exactly by the general supervised methods. Previous sentence encoders, especially BERT, specialize in modeling the relationship between source sentences. While, they have no ability to consider the overlaps of the target selected summary, and there are inherent dependencies among target labels of sentences. In this paper, we propose HAHSum (as shorthand for Hierarchical Attentive Heterogeneous Graph for Text Summarization), which well models different levels of information, including words and sentences, and spotlights redundancy dependencies between sentences. Our approach iteratively refines the sentence representations with redundancy-aware graph and delivers the label dependencies by message passing. Experiments on large scale benchmark corpus (CNN/DM, NYT, and NEWSROOM) demonstrate that HAHSum yields ground-breaking performance and outperforms previous extractive summarizers.

To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities. Although the human effort is reduced, the generated incomplete and noisy annotations pose new challenges for learning effective neural models. In this paper, we propose a novel dictionary extension method which extracts new entities through the type expanded model. Moreover, we design a multi-granularity boundaryaware network which detects entity boundaries from both local and global perspectives. We conduct experiments on different types of datasets, the results show that our model outperforms previous state-of-the-art distantly supervised systems and even surpasses the supervised models.

For sentence-level extractive summarization, there is a disproportionate ratio of selected and unselected sentences, leading to flatting the summary features when optimizing the classification. The imbalanced sentence classification in extractive summarization is inherent, which can't be addressed by data sampling or data augmentation algorithms easily. In order to address this problem, we innovatively consider the single-document extractive summarization as a rebalance problem and present a deep differential amplifier framework to enhance the features of summary sentences. Specifically, we calculate and amplify the semantic difference between each sentence and other sentences, and apply the residual unit to deepen the differential amplifier architecture. Furthermore, the corresponding objective loss of the minority class is boosted by a weighted cross-entropy. In this way, our model pays more attention to the pivotal information of one sentence, that is different from previous approaches which model all informative context in the source document. Experimental results on two benchmark datasets show that our summarizer performs competitively against state-of-the-art methods. Our source code will be available on Github.

No abstract