Event Causality Identification (ECI) focuses on extracting causal relations between events in texts.Existing methods for ECI primarily rely on causal features and external knowledge.However, these approaches fall short in two dimensions: (1) causal features between events in a text often lack explicit clues, and (2) external knowledge may introduce bias, while specific problems require tailored analyses.To address these issues, we propose SemDI -a simple and effective Semantic Dependency Inquiry Network for ECI.SemDI captures semantic dependencies within the context using a unified encoder.Then, it utilizes a Cloze Analyzer to generate a fill-in token based on comprehensive context understanding.Finally, this fill-in token is used to inquire about the causal relation between two events.Extensive experiments demonstrate the effectiveness of SemDI, surpassing state-of-the-art methods on three widely used benchmarks.Code is available at https://github.com/hrlics/SemDI.

Text summarization is to generate a brief version of a given article while maintaining its essential meaning. Most existing solutions typically relied on the standard attention-based encoder-decoder framework, where each token in the source article, including redundancy, would be contributed to the de-coder through the attention mechanism. It follows that how to filter out the redundant content becomes an important issue in the text summarization task. In this study, we propose a localness attention network, with simplicity and feasibility in mind, which circles different local regions in the source article as contributors in different decoding steps. To further strengthen the localness model, we share the semantic space of the encoder and decoder. The experimental results conducted on two benchmark datasets demonstrate the effectiveness and applicability of the proposed method in relation to several well-practiced works.

Protein-protein interaction (PPI) identification is an important task in text mining. Most PPI detection systems make predictions solely based on evidence within a single sentence and often suffer from the heavy burden of manual annotation. This paper approaches PPI detection task from a different paradigm by investigating the context of protein pairs collected from a large corpus and their relations. First, crucial cues in the context are exploited to make initial predictions. Then, relational similarity between protein pairs is calculated. Finally, evidence from the two views is integrated in the framework of minimum cuts algorithm. Experimental results show that the graph model achieves better performance than standard supervised approaches. Using 20 percent data as the training set, our algorithm achieves higher accuracy than support vector machine (SVM) using 80 percent data as training data. Moreover, the semi-supervised settings reveal promising directions for PPI identification exploiting unlabeled data.