A non-negative tensor factorization model for selectional preference induction

Non-negative Tensor Factorization (NTF) is a widely used technique for decomposing a non-negative value tensor into sparse and reasonably interpretable factors. However, NTF performs poorly when the tensor is extremely sparse, which is often the case with real-world data and higher-order tensors. In this paper, we propose Non-negative Multiple Tensor Factorization (NMTF), which factorizes the target tensor and auxiliary tensors simultaneously. Auxiliary data tensors compensate for the sparseness of the target data tensor. The factors of the auxiliary tensors also allow us to examine the target data from several different aspects. We experimentally confirm that NMTF performs better than NTF in terms of reconstructing the given data. Furthermore, we demonstrate that the proposed NMTF can successfully extract spatio-temporal patterns of people's daily life such as leisure, drinking, and shopping activity by analyzing several tensors extracted from online review data sets.

We have studied the feature extraction from sea ice SAR images based on non-negative factorization methods. The methods reported here are the sparseness-constrained non-negative matrix factorization (SC-NMF) and Non-negative tensor factorization (NTF). The studies performed show that these methods can be used to extract meaningful features from SAR images and that they can be used in sea ice SAR classification.

The main aim of this paper is to develop a new algorithm for computing a nonnegative low multi‐rank tensor approximation for a nonnegative tensor. In the literature, there are several nonnegative tensor factorizations or decompositions, and their approaches are to enforce the nonnegativity constraints in the factors of tensor factorizations or decompositions. In this paper, we study nonnegativity constraints in tensor entries directly, and a low rank approximation for the transformed tensor by using discrete Fourier transformation matrix, discrete cosine transformation matrix, or unitary transformation matrix. This strategy is particularly useful in imaging science as nonnegative pixels appear in tensor entries and a low rank structure can be obtained in the transformation domain. We propose an alternating projections algorithm for computing such a nonnegative low multi‐rank tensor approximation. The convergence of the proposed projection method is established. Numerical examples for multidimensional images are presented to demonstrate that the performance of the proposed method is better than that of nonnegative low Tucker rank tensor approximation and the other nonnegative tensor factorizations and decompositions.

A tweet is an authentic use of Natural Language where the user has to deliver the message in 140 characters or less. According to previous researchers, this restriction increases the possible ambiguity of a tweet making it difficult for traditional Natural Language Processing (NLP) tools to analyze it. This research enhances the machine learning based Stanford CoreNLP Part-of-Speech (POS) tagger with the Twitter model to extract essential keywords from a tweet. The system was enhanced using two rule-based parsers and a corpus. The research was conducted using tweets of customer service requests sent to a telecommunication company. A domain specific corpus was compiled after analyzing the tweets. The POS tagger extracted the keywords while the parsers removed any possible noise and extracted any other keywords missed by the POS tagger. The evaluation of the system was done using the Turing Test. The proposed system was tested and compared against the Stanford CoreNLP. The testing was conducted using 6 test cases, each consisting of a human keyword generator and a supervisor. In order to ensure the impartiality and intellectual diversity, the response generators and supervisors were representatives of 6 different fields. As a result of the enhancements, the Turing Test score of the system increased from 50.00% to 83.33%. The accuracy of the system could be further improved by using a complete domain specific corpus. Since the approach used theoretical linguistic features of a sentence, the same method could be employed for other NLP tools.

Applications in the World Wide Web aggregate vast amounts of information from different data sources. The aggregation process is often implemented with Extract, Transform and Load (ETL) processes. Usually ETL processes require information for aggregation available in structured formats, e. g. XML or JSON. In many cases the information is provided in natural language text which makes the application of ETL processes impractical. Due to the fact that information is provided in natural language, Information Extraction (IE) systems have been evolved. They make use of Natural Language Processing (NLP) tools to derive meaning from natural language text. State-of-the-art NLP tools apply Machine Learning methods. These NLP tools perform on newspapers with good quality, but they drop accuracy in other domains. However, to improve the quality for IE systems in specific domains often NLP tools are trained on domain specific text which is a time consuming process. This paper introduces an approach using a Continuous Integration pipeline for organizing and monitoring the annotation process on domain specific corpora.

Objective: The prevalence of moderate to severe asymptomatic carotid stenosis (ie, atherosclerotic narrowing of the extracranial carotid arteries) is generally approximately 6% and 2%, respectively. Most prior studies of carotid stenosis risk factors have been small. This study describes the development and validation of a natural language processing (NLP) tool to identify carotid stenosis and uses it to identify significant risk factors, presence, and severity of carotid stenosis. Methods: We created an NLP tool to extract the ratio of peak systolic velocity of the internal carotid artery to the common carotid artery (ICA/CCA ratio) in veterans receiving carotid duplex ultrasound examinations in the Veteran's Health Administration from 2001 to 2020. Among those who had at least one valid ICA/CCA ratio, we identified carotid stenosis severity (<50%, 50%-69%, ≥70%) based on the ICA/CCA ratio (<2, ≥2 to <4, ≥4) and assessed the association between presence and severity of carotid stenosis and clinical and demographic characteristics, including age, sex, self-identified race and ethnicity, smoking status, body mass index, systolic and diastolic blood pressures, indicator variables for pre-existing hypertension, coronary heart disease, and type 2 diabetes, and selected laboratory measures (ie, hemoglobin A1c, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, triglyceride, and creatinine). Results: The harmonic F1 score of the NLP tool was 0.907 for the right value, 0.882 for the left value, and 0.920 for the maximum value. Among the 290,517 veterans in the cohort, the median age was 68.2 years. Black patients had 16% decreased risk of more severe carotid stenosis (odds ratio: 0.84, 95% confidence interval: 0.81-0.87, P < .001). All patient-level risk factors except high-density lipoprotein cholesterol were significantly associated with carotid stenosis severity. Conclusions: The NLP tool performed well, and the study performed with our NLP-created cohort largely validates the risk factors identified by previous smaller studies, demonstrating the utility of big data and NLP in carotid stenosis research.

We present SimpleApprenant, a platform aiming to improve French L2 learners’ knowledge of Multi Word Expressions (MWEs). SimpleApprenant integrates an MWE database annotated with the Common European Framework of Reference for languages (CEFR) level and several Natural Language Processing (NLP) tools: a spelling checker, a parser, and a set of transformation rules. NLP tools and resources are used to build training and writing exercises to improve MWE knowledge and writing skills of French L2 learners. We present the user scenarios, the platform’s architecture, as well as the preliminary evaluation of its NLP tools.

This paper proposes parallel method of non-negative large sparse matrix factorization - very popular technique in computational linguistics. Proposed blocks factorization approach using Latent Dirichlet allocation, for speedup of non-negative sparse extra-large linguistic matrix and tensor factorization. The proposed method also supports the scalability of the model.

Many spectral unmixing approaches ranging from geometry, algebra to statistics have been proposed, in which nonnegative matrix factorization (NMF)-based ones form an important family. The original NMF-based unmixing algorithm loses the spectral and spatial information between mixed pixels when stacking the spectral responses of the pixels into an observed matrix. Therefore, various constrained NMF methods are developed to impose spectral structure, spatial structure, and spectral-spatial joint structure into NMF to enforce the estimated endmembers and abundances preserve these structures. Compared with matrix format, the third-order tensor is more natural to represent a hyperspectral data cube as a whole, by which the intrinsic structure of hyperspectral imagery can be losslessly retained. Extended from NMF-based methods, a matrix-vector nonnegative tensor factorization (NTF) model is proposed in this paper for spectral unmixing. Different from widely used tensor factorization models, such as canonical polyadic decomposition CPD) and Tucker decomposition, the proposed method is derived from block term decomposition, which is a combination of CPD and Tucker decomposition. This leads to a more flexible frame to model various application-dependent problems. The matrix-vector NTF decomposes a third-order tensor into the sum of several component tensors, with each component tensor being the outer product of a vector (endmember) and a matrix (corresponding abundances). From a formal perspective, this tensor decomposition is consistent with linear spectral mixture model. From an informative perspective, the structures within spatial domain, within spectral domain, and cross spectral-spatial domain are retreated interdependently. Experiments demonstrate that the proposed method has outperformed several state-of-the-art NMF-based unmixing methods.

Electronic health records (EHRs) are becoming an increasingly important source of patient information. Unfortunately, EHR data do not always directly and reliably map to medical concepts that clinical researchers need or use. Some recent studies have focused on EHR-derived phenotyping, which aims at mapping the EHR data to specific medical concepts; however, most of these approaches require labor intensive supervision from experienced clinical professionals.In this paper, we use Limestone, a nonnegative tensor factorization method to derive phenotype candidates from claims data with virtually no human supervision. Limestone represents the interactions between diagnoses and procedures among patients naturally using tensors (a generalization of matrices). The resulting tensor factors are reported as phenotype candidates that automatically reveal patient clusters on specific diagnoses and procedures. To the best of our knowledge, this is the first study that successfully extracts useful phenotypes by applying sparse nonnegative tensor factorization to a large, public-domain EHR dataset covering a broad range of diseases. Our experiments demonstrate the interpretability and the promise of high-throughput phenotypes generated from tensor factorization.KeywordsEHR phenotypingtensor factorizationdimensionality reduction

In order to achieve best neutron flux-mapping within nuclear research reactors, we investigate in this paper, the application of blind source separation algorithms to extract different independent components that form the fission chamber output signals. More specifically, we simulated the fission chamber using python-based of Fission Chambers (pyFC) code suite. The resulting simulated signals are considered observation vectors. They are then, processed via nonnegative matrix and tensor factorization (NMF&NTF) methods to isolate the independent components that form a neutron signal. Thus, in order to select the most efficient one to analyze our set of data, various algorithms have been tested and classified according to their performance index of separability (PI). The extracted independent components have been used to characterize neutron signal through spectrogram time-frequency representation. Obtained results will be illustrated and discussed.

Purpose This study explores the potential of Natural Language Processing (NLP) tools, specifically ChatGPT-4o and Data Analyst, in supporting health commissions with disability assessments. Methods Nine realistic patient scenarios were created to reflect typical cases in disability evaluations, encompassing conditions like stroke, cerebral palsy, traumatic injuries, and hereditary disorders, each involving varied motor and functional impairments. These scenarios were input into ChatGPT-4o and Data Analyst. Their outputs were evaluated using a 5-point Likert scale on alignment with expert guidelines, completeness, and lack of false information. Interrater reliability was established before scoring. Results Both models produced generally high-quality narrative reports, ChatGPT-4o was rated “very good” and Data Analyst “good,” with no statistically significant difference in overall scores. However, ChatGPT-4o failed to calculate correct disability percentages in 55.6%, and Data Analyst failed in 88.9% of scenarios. Conclusions While NLP tools can assist in generating structured disability reports, they currently lack the precision needed for calculating disability percentages reliably. Expert oversight remains essential for decision-making in disability assessments.

The US Food and Drug Administration Adverse Event Reporting System (FAERS) contains over 24 million individual case safety reports (ICSRs). In this research project, we evaluated a natural language processing (NLP) tool’s ability to extract four demographic variables (gender, weight, ethnicity, race) from ICSR narratives. Specificity of the NLP algorithm was over 94% for all demographics, while sensitivity varied between the demographics: 98.6% (gender), 45.5% (weight), 100% (ethnicity), and 85.3% (race). Among ICSRs missing weight, ethnicity, and race in the structured field, few cases had this information in the narrative (&amp;gt;95% missing); consequently, the positive predictive value (PPV) for these three demographics had wide 95% confidence intervals. After NLP implementation, the total number of ICSRs missing gender was reduced by 33% (i.e., NLP identified 472 thousand reports having a gender value in the narrative that was not in the structured field), while the total number of ICSRs missing weight, ethnicity, or race was reduced by less than 4%. This study demonstrated that the implementation of an NLP tool can provide meaningful improvements in the availability of gender information for pharmacovigilance activities conducted with FAERS data. In contrast, NLP tools targeting the extraction of weight, ethnicity, or race from free-text fields have minimal impact largely because the information was infrequently provided by the reporter. Further gains in completeness of these fields must originate from increases in provision of demographic information from the reporter rather than informatic solutions.

The aim of this study was to test the ability of a commercially available natural language processing (NLP) tool to accurately extract examination quality-related and large polyp information from colonoscopy reports with varying report formats. Colonoscopy quality reporting often requires manual data abstraction. NLP is another option for extracting information; however, limited data exist on its ability to accurately extract examination quality and polyp findings from unstructured text in colonoscopy reports with different reporting formats. NLP strategies were developed using 500 colonoscopy reports from Kaiser Permanente Northern California and then tested using 300 separate colonoscopy reports that underwent manual chart review. Using findings from manual review as the reference standard, we evaluated the NLP tool's sensitivity, specificity, positive predictive value (PPV), and accuracy for identifying colonoscopy examination indication, cecal intubation, bowel preparation adequacy, and polyps ≥10 mm. The NLP tool was highly accurate in identifying examination quality-related variables from colonoscopy reports. Compared with manual review, sensitivity for screening indication was 100% (95% confidence interval: 95.3%-100%), PPV was 90.6% (82.3%-95.8%), and accuracy was 98.2% (97.0%-99.4%). For cecal intubation, sensitivity was 99.6% (98.0%-100%), PPV was 100% (98.5%-100%), and accuracy was 99.8% (99.5%-100%). For bowel preparation adequacy, sensitivity was 100% (98.5%-100%), PPV was 100% (98.5%-100%), and accuracy was 100% (100%-100%). For polyp(s) ≥10 mm, sensitivity was 90.5% (69.6%-98.8%), PPV was 100% (82.4%-100%), and accuracy was 95.2% (88.8%-100%). NLP yielded a high degree of accuracy for identifying examination quality-related and large polyp information from diverse types of colonoscopy reports.

Evaluation of Natural Language Processing (NLP) systems to annotate drug product labeling with MedDRA terminology