Nested term recognition driven by word connection strength

Terminology ◽  
2015 ◽  
Vol 21 (2) ◽  
pp. 180-204 ◽  
Author(s):  
Malgorzata Marciniak ◽  
Agnieszka Mykowiecka
Keyword(s):  
Mutual Information ◽  
Term Structure ◽  
Recognition Task ◽  
New Method ◽  
Connection Strength ◽  
Term List ◽  
C Value ◽  
Automatic Term Recognition ◽  
The Impact ◽  
Value Ranking

Domain corpora are often not very voluminous and even important terms can occur in them not as isolated maximal phrases but only within more complex constructions. Appropriate recognition of nested terms can thus influence the content of the extracted candidate term list and its order. We propose a new method for identifying nested terms based on a combination of two aspects: grammatical correctness and normalised pointwise mutual information (NPMI) counted for all bigrams in a given corpus. NPMI is typically used for recognition of strong word connections, but in our solution we use it to recognise the weakest points to suggest the best place for division of a phrase into two parts. By creating, at most, two nested phrases in each step, we introduce a binary term structure. We test the impact of the proposed method applied, together with the C-value ranking method, to the automatic term recognition task performed on three corpora, two in Polish and one in English.

Automatic Term Recognition Using Hybrid Method Based on Rewriting and Statistic

2014 ◽  
Vol 1049-1050 ◽  
pp. 1544-1549
Author(s):  
Wen Xiong
Keyword(s):  
Mutual Information ◽  
Hybrid Method ◽  
Deep Processing ◽  
Patent Data ◽  
Two Phase ◽  
Statistical Measures ◽  
Log Likelihood ◽  
C Value ◽  
Automatic Term Recognition ◽  
Significant Application

Machine aided human translation (MAHT) for the abstract of patent texts is an important step to the deep processing of the patent data, where the terms have significant application value. This paper investigates the automatic term recognition (ATR), and proposes a new hybrid method based on two-phase analysis and statistic to generate English candidate terms. The segments including stop words were not simply discarded; instead, a rewriting method using beginning patterns, ending patterns, and inner patterns on the phase two was employed for the processing of the segments. In the meantime, generalized statistical measures were used for the evaluation of the candidates such as the generalized mutual information (MI), Log-Likelihood Ratio (LLR), and C-value to filter the low score’s candidate terms and to attain the intersection set of them. The experiments on the patent abstract texts extracted randomly show the availability of the method.

A new method showing the impact of pulp refining on fiber-fiber interactions in wet webs

2016 ◽  
Vol 31 (2) ◽  
pp. 205-212 ◽  
Author(s):  
Belle Jürgen ◽  
Kleemann Stephan ◽  
Odermatt Jürgen ◽  
Olbrich Andrea
Keyword(s):  
New Method ◽  
The Impact

The Impact of News on the Term-Structure of Breakeven Inflation

2009 ◽  
Author(s):  
Anthony P. Rodrigues ◽  
Michelle Steinberg ◽  
Laurel Madar
Keyword(s):  
Term Structure ◽  
The Impact

Design of a Robust Memristive Spiking Neuromorphic System with Unsupervised Learning in Hardware

2021 ◽  
Vol 17 (4) ◽  
pp. 1-26
Author(s):  
Md Musabbir Adnan ◽  
Sagarvarma Sayyaparaju ◽  
Samuel D. Brown ◽  
Mst Shamim Ara Shawkat ◽  
Catherine D. Schuman ◽  
...  
Keyword(s):  
Unsupervised Learning ◽  
Recognition Task ◽  
Single Layer ◽  
Process Variations ◽  
Spike Timing ◽  
System Level ◽  
Design Parameters ◽  
Digital Pulse ◽  
Neuromorphic System ◽  
The Impact

Spiking neural networks (SNN) offer a power efficient, biologically plausible learning paradigm by encoding information into spikes. The discovery of the memristor has accelerated the progress of spiking neuromorphic systems, as the intrinsic plasticity of the device makes it an ideal candidate to mimic a biological synapse. Despite providing a nanoscale form factor, non-volatility, and low-power operation, memristors suffer from device-level non-idealities, which impact system-level performance. To address these issues, this article presents a memristive crossbar-based neuromorphic system using unsupervised learning with twin-memristor synapses, fully digital pulse width modulated spike-timing-dependent plasticity, and homeostasis neurons. The implemented single-layer SNN was applied to a pattern-recognition task of classifying handwritten-digits. The performance of the system was analyzed by varying design parameters such as number of training epochs, neurons, and capacitors. Furthermore, the impact of memristor device non-idealities, such as device-switching mismatch, aging, failure, and process variations, were investigated and the resilience of the proposed system was demonstrated.

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

EXPRESS: Bored, distracted and forgetful – The impact of mind wandering and boredom on memory encoding

2021 ◽  
pp. 174702182110263
Author(s):  
Philippe Blondé ◽  
Marco Sperduti ◽  
Dominique Makowski ◽  
Pascale Piolino
Keyword(s):  
Working Memory ◽  
Memory Load ◽  
Memory Performance ◽  
Load Condition ◽  
Recognition Task ◽  
Mind Wandering ◽  
Memory Encoding ◽  
Working Memory Load ◽  
Thought Probes ◽  
The Impact

Mind wandering, defined as focusing attention toward task unrelated thoughts, is a common mental state known to impair memory encoding. This phenomenon is closely linked to boredom. Very few studies, however, have tested the potential impact of boredom on memory encoding. Thus, the present study aimed at manipulating mind wandering and boredom during an incidental memory encoding task, to test their differential impact on memory encoding. Thirty-two participants performed a variant of the n-back task in which they had to indicate if the current on-screen object was the same as the previous one (1-back; low working memory load) or the one presented three trials before (3-back; high working memory load). Moreover, thought probes assessing either mind wandering or boredom were randomly presented. Afterward, a surprise recognition task was delivered. Results showed that mind wandering and boredom were highly correlated, and both decreased in the high working memory load condition, while memory performance increased. Although both boredom and mind wandering predicted memory performance taken separately, we found that mind wandering was the only reliable predictor of memory performance when controlling for boredom and working memory load. Model comparisons also revealed that a model with boredom only was outperformed by a model with mind wandering only and a model with both mind wandering and boredom, suggesting that the predictive contribution of boredom in the complete model is minimal. The present results confirm the high correlation between mind wandering and boredom and suggest that the hindering effect of boredom on memory is subordinate to the effect of mind wandering.

scholarly journals A new method of inferring the size, number density, and charge of mesospheric dust from its in situ collection by the DUSTY probe

2019 ◽  
Vol 12 (3) ◽  
pp. 1673-1683 ◽  
Author(s):  
Ove Havnes ◽  
Tarjei Antonsen ◽  
Gerd Baumgarten ◽  
Thomas W. Hartquist ◽  
Alexander Biebricher ◽  
...  
Keyword(s):  
New Method ◽  
Production Model ◽  
Dust Particles ◽  
Bottom Plate ◽  
Charged Dust ◽  
Fundamental Parameters ◽  
Dust Charge ◽  
Analysis Technique ◽  
June July ◽  
The Impact

Abstract. We present a new method of analyzing measurements of mesospheric dust made with DUSTY rocket-borne Faraday cup probes. It can yield the variation in fundamental dust parameters through a mesospheric cloud with an altitude resolution down to 10 cm or less if plasma probes give the plasma density variations with similar height resolution. A DUSTY probe was the first probe that unambiguously detected charged dust and aerosol particles in the Earth's mesosphere. DUSTY excluded the ambient plasma by various biased grids, which however allowed dust particles with radii above a few nanometers to enter, and it measured the flux of charged dust particles. The flux measurements directly yielded the total ambient dust charge density. We extend the analysis of DUSTY data by using the impact currents on its main grid and the bottom plate as before, together with a dust charging model and a secondary charge production model, to allow the determination of fundamental parameters, such as dust radius, charge number, and total dust density. We demonstrate the utility of the new analysis technique by considering observations made with the DUSTY probes during the MAXIDUSTY rocket campaign in June–July 2016 and comparing the results with those of other instruments (lidar and photometer) also used in the campaign. In the present version we have used monodisperse dust size distributions.

scholarly journals Qualitative Recognition of Primary Taste Sensation Based on Surface Electromyography

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 4994
Author(s):  
You Wang ◽  
Hengyang Wang ◽  
Huiyan Li ◽  
Asif Ullah ◽  
Ming Zhang ◽  
...  
Keyword(s):  
Surface Electromyography ◽  
Model Performance ◽  
Recognition Task ◽  
Taste Sensation ◽  
Pass Filter ◽  
Power Frequency ◽  
Coffee Powder ◽  
Adaptive Power ◽  
Feature Dimension ◽  
The Impact

Based on surface electromyography (sEMG), a novel recognition method to distinguish six types of human primary taste sensations was developed, and the recognition accuracy was 74.46%. The sEMG signals were acquired under the stimuli of no taste substance, distilled vinegar, white granulated sugar, instant coffee powder, refined salt, and Ajinomoto. Then, signals were preprocessed with the following steps: sample augments, removal of trend items, high-pass filter, and adaptive power frequency notch. Signals were classified with random forest and the classifier gave a five-fold cross-validation accuracy of 74.46%, which manifested the feasibility of the recognition task. To further improve the model performance, we explored the impact of feature dimension, electrode distribution, and subject diversity. Accordingly, we provided an optimized feature combination that reduced the number of feature types from 21 to 4, a preferable selection of electrode positions that reduced the number of channels from 6 to 4, and an analysis of the relation between subject diversity and model performance. This study provides guidance for further research on taste sensation recognition with sEMG.

Sign in / Sign up

Export Citation Format

Share Document