Disambiguating named entities in natural-language text maps mentions of ambiguous names onto canonical entities like people or places, registered in a knowledge base such as DBpedia or YAGO. This paper presents a robust method for collective disambiguation, by harnessing context from knowledge bases and using a new form of coherence graph. It unifies prior approaches into a comprehensive framework that combines three measures: the prior probability of an entity being mentioned, the similarity between the contexts of a mention and a candidate entity, as well as the coherence among candidate entities for all mentions together. The method builds a weighted graph of mentions and candidate entities, and computes a dense subgraph that approximates the best joint mention-entity mapping. Experiments show that the new method significantly outperforms prior methods in terms of accuracy, with robust behavior across a variety of inputs.

/pdf/robust-disambiguation-of-named-entities-in-text-2nql8lmxop.pdf

Robust Disambiguation of Named Entities in Text

Social big data

The following report is intended to provide an overview of the current state of the literature on the relationship between social media; political polarization; and political “disinformation,” a term used to encompass a wide range of types of information about politics found online, including “fake news,” rumors, deliberately factually incorrect information, inadvertently factually incorrect information, politically slanted information, and “hyperpartisan” news. The review of the literature is provided in six separate sections, each of which can be read individually but that cumulatively are intended to provide an overview of what is known — and unknown — about the relationship between social media, political polarization, and disinformation. The report concludes by identifying key gaps in our understanding of these phenomena and the data that are needed to address them.

/pdf/social-media-political-polarization-and-political-4o1xubc6fc.pdf

Social media, political polarization, and political disinformation: a review of the scientific literature

Owing to improvements in image recognition via deep learning, machine-learning algorithms could eventually be applied to automated medical diagnoses that can guide clinical decision-making. However, these algorithms remain a 'black box' in terms of how they generate the predictions from the input data. Also, high-performance deep learning requires large, high-quality training datasets. Here, we report the development of an understandable deep-learning system that detects acute intracranial haemorrhage (ICH) and classifies five ICH subtypes from unenhanced head computed-tomography scans. By using a dataset of only 904 cases for algorithm training, the system achieved a performance similar to that of expert radiologists in two independent test datasets containing 200 cases (sensitivity of 98% and specificity of 95%) and 196 cases (sensitivity of 92% and specificity of 95%). The system includes an attention map and a prediction basis retrieved from training data to enhance explainability, and an iterative process that mimics the workflow of radiologists. Our approach to algorithm development can facilitate the development of deep-learning systems for a variety of clinical applications and accelerate their adoption into clinical practice.

An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets

https://digitalcommons.njit.edu/cgi/viewcontent.cgi?article=2507&context=dissertations

Early detection of fake news on social media

We present a novel method based on interdependent representations of short texts for determining their degree of semantic similarity. The method represents each short text as two dense vectors: the former is built using the word-to-word similarity based on pre-trained word vectors, the latter is built using the word-to-word similarity based on external sources of knowledge. We also developed a preprocessing algorithm that chains coreferential named entities together and performs word segmentation to preserve the meaning of phrasal verbs and idioms. We evaluated the proposed method on three popular datasets, namely Microsoft Research Paraphrase Corpus, STS2015 and P4PIN, and obtained state-of-the-art results on all three without using prior knowledge of natural language, e.g., part-of-speech tags or parse tree, which indicates the interdependent representations of short text pairs are effective and efficient for semantic textual similarity tasks.

Learning short-text semantic similarity with word embeddings and external knowledge sources

Data mining is one of exciting fields in recent years. Its purpose is to discover useful information and knowledge from large databases for business decisions and other areas. One engineering topic of data mining is utility mining which discovers high-utility itemsets. An itemset in traditional utility mining considers individual profits and quantities of items in transactions regardless of its length. The average-utility measure is then proposed. This measure is the total utility of an itemset divided by the number of items. Several mining algorithms were also proposed for mining high average-utility itemsets (HAUIs) from a transactional database. However, the number of generated candidates is very large since an itemset is not a HAUI, but itemsets generated from it and others can be HAUIs. Some effective approaches have been proposed to prune candidates and save time. This paper proposes a new method to mine HAUI from transaction databases. The advantage of this method is to reduce candidates efficiently by using HAUI-Tree. A new itemset structure is also developed to improve the speed of calculating the values of itemsets and optimize the memory usage.

/pdf/a-new-method-for-mining-high-average-utility-itemsets-4gr9ww3f6v.pdf

A New Method for Mining High Average Utility Itemsets

Online social networks have become an effective and important social platform for communication, opinions exchange, and information sharing. However, they also make it possible for rapid and wide misinformation diffusion, which may lead to pernicious influences on individuals or society. Hence, it is extremely important and necessary to detect the misinformation propagation by placing monitors.In this article, we first define a general misinformation-detection problem for the case where the knowledge about misinformation sources is lacking, and show its equivalence to the influence-maximization problem in the reverse graph. Furthermore, considering node vulnerability, we aim to detect the misinformation reaching to a specific user. Therefore, we study a τ-Monitor Placement problem for cases where partial knowledge of misinformation sources is available and prove its nP complexity. We formulate a corresponding integer program, tackle exponential constraints, and propose a Minimum Monitor Set Construction (MMSC) algorithm, in which the cut-set2 has been exploited in the estimation of reachability of node pairs. Moreover, we generalize the problem from a single target to multiple central nodes and propose another algorithm based on a Monte Carlo sampling technique. Extensive experiments on real-world networks show the effectiveness of proposed algorithms with respect to minimizing the number of monitors.

Misinformation in Online Social Networks: Detect Them All with a Limited Budget

We propose an approach to diagnosing brain hemorrhage by using deep learning. In particular, three types of convolutional neural networks that are LeNet, GoogLeNet, and Inception-ResNet are employed. In the training phase, we only train the last fully-connected layers of GoogLeNet and Inception-ResNet, but do train all layers of LeNet. We build a dataset consisting of 100 cases collected from the 115 Hospital, Ho Chi Minh City, Vietnam. The experimental results show that LeNet, GoogLeNet, and Inception-ResNet achieve accuracy of 0.997, 0.982, and 0.992 respectively on the dataset. Through experimental results, we found that convolutional neural networks are pre-trained with non-medical images like GoogLeNet or Inception-ResNet can be used in medical image diagnosis, particularly in brain hemorrhage diagnosis. And, we confirm that among the three deep models, LeNet is the most time-consuming model.

Brain Hemorrhage Diagnosis by Using Deep Learning

Currently, for named entity disambiguation, the short-age of training data is a problem. This paper presents a novel method that overcomes this problem by automatically generating an annotated corpus based on a specific ontology. Then the corpus was enriched with new and informative features extracted from Wikipedia data. Moreover, rather than pursuing rule-based methods as in literature, we employ a machine learning model to not only disambiguate but also identify named entities. In addition, our method explores in details the use of a range of features extracted from texts, a given ontology, and Wikipedia data for disambiguation. This paper also systematically analyzes impacts of the features on disambiguation accuracy by varying their combinations for representing named entities. Empirical evaluation shows that, while the ontology provides basic features of named entities, Wikipedia is a fertile source for additional features to construct accurate and robust named entity disambiguation systems.

Hien T. Nguyen

Papers

Learning short-text semantic similarity with word embeddings and external knowledge sources

A New Method for Mining High Average Utility Itemsets

Misinformation in Online Social Networks: Detect Them All with a Limited Budget

Brain Hemorrhage Diagnosis by Using Deep Learning

Named entity disambiguation on an ontology enriched by Wikipedia