We devise a neural network-based temporal-textual framework that generates subgraphs with highly correlated authors from short-text contents. Our approach computes the relevance score (edge weight) between authors by considering a portmanteau of contents and concepts. It then employs a stack-wise graph-cutting algorithm to extract communities of related authors. Experimental results show that our multi-aspect vector space model can gain higher performance than other knowledge-centered competitors in linking short-text authors.

We devise a neural network-based temporal-textual framework that generates subgraphs with highly correlated authors from short-text contents. Our approach computes the relevance score (edge weight) between authors by considering a portmanteau of contents and concepts. It then employs a stack-wise graph-cutting algorithm to extract communities of related authors. Experimental results show that our multi-aspect vector space model can gain higher performance than other knowledge-centered competitors in linking short-text authors.

Addressing the challenge of matching queries with the right experts amid temporal-textual inconsistencies, we present a novel approach that combines an attention-based text embedding model with a continuous-time module. This method effectively maps queries to relevant experts by analyzing concept-oriented vectors and user behavior, demonstrating significant effectiveness on StackOverflow and Yahoo datasets.

Entity alignment (EA) aims to identify equivalent entities between knowledge graphs (KGs), which is a key technique to improve the coverage of existing KGs. Current EA models largely ignore the importance of time information contained in KGs and treat relational facts or attribute values of entities as time-invariant. However, real-world entities could evolve over time, making the knowledge of the aligned entities very different in multiple KGs. This may cause incorrect matching between KGs if such entity dynamics is ignored. In this paper, we propose a time-aware entity alignment (TEA) model that discovers the entity evolving behaviour by exploring the time contexts in KGs and aggregates various contextual information to make the alignment decision. In particular, we address two main challenges in the TEA model: 1) How to identify highly-correlated temporal facts; 2) How to capture entity dynamics and incorporate it to learn a more informative entity representation for the alignment task. Experiments on real-world datasets1 verify the superiority of our TEA model over state-of-the-art entity aligners.

Finding the most suitable individual to answer a question using brief content has important usages, including the community of question answering systems and online recommender frameworks. However, one must tackle challenges: Disregarding the indispensable noise in short text contents, authors usually answer the input query with mismatched words that can negatively influence the textual relevance. Moreover, many vocabularies imply various alterations. Finally, not every expert is eager to answer an input query given the time constraint, named the reluctance dilemma. To overcome the challenges, we devise a novel embedding approach that constructs context-aware vectors. We then extract the knowledge domains out of the online contextual content. While we track user textual-temporal behavioral patterns via an infinite continuous-time module, we recommend a set of experts pertinent to the given query and willingly provide the response during the expected time. Experimental results on two real-world datasets ofStackOverflowandYahooshow that our online time-sensitive value-wise transformer can achieve higher effectiveness and efficiency versus other trending rivals in online expert recommendation systems. In addition, we empirically experience that Fourier transformers can automatically infer multi-aspect base signals and overpass manual discrete-time models in obtaining time-specific user profiles.

Abstract Auto-regressive extractive summarization approaches determine sentence extraction probability conditioning on previous decisions by maintaining a partial summary representation. Despite its popularity, the framework has two main drawbacks: 1) the partial summary representation is irresolutely denoted by a weighted summation of all the processed sentences without any filtering, resulting in a noisy representation and degrading the effectiveness of extracting subsequent sentences; 2) earlier sentences are biased towards a higher extraction probability due to the sequential nature of sequence tagging. To address these two problems, we propose the Auto-regressive Extractive Summarization with Replacement (AES-Rep), a novel auto-regressive extractive summarization model. In particular, the AES-Rep model consists of two main modules: the extraction decision module that determines whether a sentence should be extracted, and the replacement locater module that enables extracted deficient sentences to be replaced with latter sentences by comparing their expressiveness with respect to the main idea of the document. These modules update the partial summary with explicit actions using elaborated multidimensional guidance. We conduct extensive experiments on the benchmark CNN and DailyMail datasets. Experimental results show that AES-Rep can achieve better performance compared with various strong baselines in terms of multiple ROUGE metrics.

Linking authors of short-text contents has important usages in many applications, including Named Entity Recognition (NER) and human community detection. However, certain challenges lie ahead. First, the input short-text contents are noisy, ambiguous, and do not follow the grammatical rules. Second, traditional text mining methods fail to effectively extract concepts through words and phrases. Third, the textual contents are temporally skewed, which can affect the semantic understanding by multiple time facets. Finally, using knowledge-bases can make the results biased to the content of the external database and deviate the meaning from the input short text corpus. To overcome these challenges, we devise a neural network-based temporal-textual framework that generates the subgraphs with highly correlated authors from short-text contents. Our approach, on the one hand, computes the relevance score (edge weight) between the authors through considering a portmanteau of contents and concepts, and on the other hand, employs a stack-wise graph cutting algorithm to extract the communities of the related authors. Experimental results show that compared to other knowledge-centered competitors, our multi-aspect vector space model can achieve a higher performance in linking short-text authors. In addition, given the author linking task, the more comprehensive the dataset is, the higher the significance of the extracted concepts will be.

An alarm is raised due to a defect in a transportation system. Given a graph over which the alarms propagate, we aim to exploit a set of subgraphs with highly correlated nodes (or entities). The edge weight between each pair of entities can be computed using the temporal dynamics of the propagation process. We retrieve the top k edge weights and each group of connected entities can consequently form a tightly coupled subgraph. However, numerous challenges abound. First, the textual contents associated with the alarms of the same type differ during the propagation process. Hence, in the lack of textual data, the temporal information can only be employed to compute the correlation weights. Second, in many scenarios, the same alarm does not propagate. Third, given a pair of entities, the propagation can occur in both directions. Most of the prior work only consider the time-window and assume that the propagation between a pair of entities occurs sequentially. But, the propagation process should be inferred using miscellaneous temporal features. Therefore, we devise a generative approach that, on the one hand, utilizes infinite temporal latent factors (e.g. hour, day, and etc.) to compute the correlation weights, and on the other hand, analyzes how an alarm in one entity can cause a set of alarms in another. We also conduct an extensive set of experiments to compare the performance of the subgraph mining methods. The results show that our unified framework can effectively exploit the tightly coupled subgraphs.