Subevents elaborate an event and widely exist in event descriptions. Subevent knowledge is useful for discourse analysis and event-centric applications. Acknowledging the scarcity of subevent knowledge, we propose a weakly supervised approach to extract subevent relation tuples from text and build the first large scale subevent knowledge base. We first obtain the initial set of event pairs that are likely to have the subevent relation, by exploiting two observations that 1) subevents are temporally contained by the parent event, and 2) the definitions of the parent event can be used to further guide the identification of subevents. Then, we collect rich weak supervision using the initial seed subevent pairs to train a contextual classifier using BERT and apply the classifier to identify new subevent pairs. The evaluation showed that the acquired subevent tuples (239K) are of high quality (90.1% accuracy) and cover a wide range of event types. The acquired subevent knowledge has been shown useful for discourse analysis and identifying a range of event-event relations.

We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances attentions over contexts and constraints through adding a regularization term into the objective function. Experiments show that our knowledge regularization approach outperforms all previous systems on the benchmark dataset PDTB for discourse parsing.

We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure. With the goal of improving implicit discourse relation classification, we introduce a paragraph-level neural networks that model inter-dependencies between discourse units as well as discourse relation continuity and patterns, and predict a sequence of discourse relations in a paragraph. Experimental results show that our model outperforms the previous state-of-the-art systems on the benchmark corpus of PDTB.

Capabilities to categorize a clause based on the type of situation entity (e.g., events, states and generic statements) the clause introduces to the discourse can benefit many NLP applications. Observing that the situation entity type of a clause depends on discourse functions the clause plays in a paragraph and the interpretation of discourse functions depends heavily on paragraph-wide contexts, we propose to build context-aware clause representations for predicting situation entity types of clauses. Specifically, we propose a hierarchical recurrent neural network model to read a whole paragraph at a time and jointly learn representations for all the clauses in the paragraph by extensively modeling context influences and inter-dependencies of clauses. Experimental results show that our model achieves the state-of-the-art performance for clause-level situation entity classification on the genre-rich MASC+Wiki corpus, which approaches human-level performance.

Journalists usually organize and present the contents of a news article following a well-defined structure. In this work, we propose a new task to categorize news articles based on their content presentation structures, which is beneficial for various NLP applications. We first define a small set of news elements considering their functions (e.g., introducing the main story or event, catching the reader’s attention and providing details) in a news story and their writing style (narrative or expository), and then formally define four commonly used news article structures based on their selections and organizations of news elements. We create an annotated dataset for structure-based news genre identification, and finally, we build a predictive model to assess the feasibility of this classification task using structure indicative features.

Focusing on the task of identifying event temporal status, we find that events directly or indirectly governing the target event in a dependency tree are most important contexts. Therefore, we extract dependency chains containing context events and use them as input in neural network models, which consistently outperform previous models using local context words as input. Visualization verifies that the dependency chain representation can effectively capture the context events which are closely related to the target event and play key roles in predicting event temporal status.

The lack of large realistic datasets presents a bottleneck in online deception detection studies. In this paper, we apply a data collection method based on social network analysis to quickly identify high quality deceptive and truthful online reviews1 from Amazon. The dataset contains more than 10,000 deceptive reviews and is diverse in product domains and reviewers. Using this dataset, we explore effective general features for online deception detection that perform well across domains. We demonstrate that with generalized features – advertising speak and writing complexity scores – deception detection performance can be further improved by adding additional deceptive reviews from assorted domains in training. Finally, reviewer level evaluation gives an interesting insight into different deceptive reviewers’ writing styles.