Abstract This paper summarizes ongoing research in Natural-Language-Processing-driven citation analysis and describes experiments and motivating examples of how this work can be used to enhance traditional scientometrics analysis that is based on simply treating citations as a ‘vote’ from the citing paper to cited paper. In particular, we describe our dataset for citation polarity and citation purpose, present experimental results on the automatic detection of these indicators, and demonstrate the use of such annotations for studying research dynamics and scientific summarization. We also look at two complementary problems that show up in Natural-Language-Processing-driven citation analysis for a specific target paper. The first problem is extracting citation context, the implicit citation sentences that do not contain explicit anchors to the target paper. The second problem is extracting reference scope, the target relevant segment of a complicated citing sentence that cites multiple papers. We show how these tasks can be helpful in improving sentiment analysis and citation-based summarization.

The increasing pervasiveness of social media creates new opportunities to study human social behavior, while challenging our capability to analyze their massive data streams. One of the emerging tasks is to distinguish between different kinds of activities, for example engineered misinformation campaigns versus spontaneous communication. Such detection problems require a formal definition of meme, or unit of information that can spread from person to person through the social network. Once a meme is identified, supervised learning methods can be applied to classify different types of communication. The appropriate granularity of a meme, however, is hardly captured from existing entities such as tags and keywords. Here we present a framework for the novel task of detecting memes by clustering messages from large streams of social data. We evaluate various similarity measures that leverage content, metadata, network features, and their combinations. We also explore the idea of pre-clustering on the basis of existing entities. A systematic evaluation is carried out using a manually curated dataset as ground truth. Our analysis shows that pre-clustering and a combination of heterogeneous features yield the best trade-off between number of clusters and their quality, demonstrating that a simple combination based on pairwise maximization of similarity is as effective as a non-trivial optimization of parameters. Our approach is fully automatic, unsupervised, and scalable for real-time detection of memes in streaming data.

The continuation of Moore's law scaling, but in the absence of Dennard scaling, motivates an emphasis on energy-efficient accelerator-based designs for future applications. In natural language processing, the conventional approach to automatically analyze vast text collections - using scale-out processing - incurs high energy and hardware costs since the central compute-intensive step of similarity measurement often entails pairwise, all-to-all comparisons. We propose a custom hardware accelerator for similarity measures that leverages data streaming, memory latency hiding, and parallel computation across variable-length threads. We evaluate our design through a combination of architectural simulation and RTL synthesis. When executing the dominant kernel in a semantic indexing application for documents, we demonstrate throughput gains of up to 42× and 58× lower energy per similarity-computation compared to an optimized software implementation, while requiring less than 1.3% of the area of a conventional core.

Researchers and scientists increasingly find themselves in the position of having to quickly understand large amounts of technical material. Our goal is to effectively serve this need by using bibliometric text mining and summarization techniques to generate summaries of scientific literature. We show how we can use citations to produce automatically generated, readily consumable, technical extractive summaries. We first propose C-LexRank, a model for summarizing single scientific articles based on citations, which employs community detection and extracts salient information-rich sentences. Next, we further extend our experiments to summarize a set of papers, which cover the same scientific topic. We generate extractive summaries of a set of Question Answering (QA) and Dependency Parsing (DP) papers, their abstracts, and their citation sentences and show that citations have unique information amenable to creating a summary.

In this paper, we model the pair-wise similarities of a setof documents as a weighted network with a single cutoffparameter. Such a network can be thought of an ensemble of unweighted graphs, each consisting of edges withweights greater than the cutoff value. We look at this network ensemble as a complex system with a temperature parameter, and refer to it as a Latent Network. Ourexperiments on a number of datasets from two different domains show that certain properties of latent networks like clustering coefficient, average shortest path,and connected components exhibit patterns that are significantly divergent from randomized networks. We explain that these patterns reflect the network phase transition as well as the existence of a community structure in document collections. Using numerical analysis,we show that we can use the aforementioned networkproperties to predicts the clustering Normalized MutualInformation (NMI) with high correlation (rho > 0.9). Finally we show that our clustering method significantlyoutperforms other baseline methods (NMI > 0.5)

Abstract Gaining a rapid overview of an emerging scientific topic, sometimes called research fronts, is an increasingly common task due to the growing amount of interdisciplinary collaboration. Visual overviews that show temporal patterns of paper publication and citation links among papers can help researchers and analysts to see the rate of growth of topics, identify key papers, and understand influences across subdisciplines. This article applies a novel network‐visualization tool based on meaningful layouts of nodes to present research fronts and show citation links that indicate influences across research fronts. To demonstrate the value of two‐dimensional layouts with multiple regions and user control of link visibility, we conducted a design‐oriented, preliminary case study with 6 domain experts over a 4‐month period. The main benefits were being able (a) to easily identify key papers and see the increasing number of papers within a research front, and (b) to quickly see the strength and direction of influence across related research fronts.

Abstract: Ontology matching is a process for selection of a good alignment across entities of two (or more) ontologies. This can be viewed as a two‐phase process of (1) applying a similarity measure to find the correspondence of each pair of entities from two ontologies, and (2) extraction of an optimal or near optimal mapping. This paper is focused on the second phase and introduces our evolutionary approach for that. To be able to do so, we need a mechanism to score different possible mappings. Our solution is a weighting mechanism named coincidence‐based weighting. A genetic algorithm is then introduced to create better mappings in successive iterations. We will explain how we code a mapping as well as our crossover and mutation functions. Evaluation of the algorithm is shown and discussed.