scholarly journals Unsupervised Neural Aspect Extraction with Sememes

2019 ◽  
Author(s):  
Ling Luo ◽  
Xiang Ao ◽  
Yan Song ◽  
Jinyao Li ◽  
Xiaopeng Yang ◽  
...  
Keyword(s):  
Real World ◽  
Latent Variables ◽  
Lexical Semantics ◽  
Word Meanings ◽  
Lexical Semantic ◽  
Aspect Extraction ◽  
Real World Datasets ◽  
Semantic Resources

Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts. To enhance the performance on aspect extraction, leveraging lexical semantic resources is a possible solution to such challenge. In this paper, we present an unsupervised neural framework that leverages sememes to enhance lexical semantics. The overall framework is analogous to an autoenoder which reconstructs sentence representations and learns aspects by latent variables. Two models that form sentence representations are proposed by exploiting sememes via (1) a hierarchical attention; (2) a context-enhanced attention. Experiments on two real-world datasets demonstrate the validity and the effectiveness of our models, which significantly outperforms existing baselines.

THE VALENCE PROPERTY OF NEOLOGISMS IN KAZAKH LANGUAGE

2020 ◽  
Vol 73 (3) ◽  
pp. 14-21
Author(s):  
A. Amirbekova ◽  
Keyword(s):  
Lexical Semantics ◽  
Broad Sense ◽  
Practical Significance ◽  
Word Meanings ◽  
Lexical Semantic ◽  
The Given

The article deals with the concept of valency as a phenomenon lying at the confluence of syntax and lexical semantics. The paper also represents types of valency, directions in which the theory of valency is considered. Valency in the broad sense of the word refers to the capacity of a language unit to enter into communication with other units of a particular order. Objectivity and scientific and practical significance of the theory of valency is determined by the lexical-semantic potential of the word. Semantic valency is based on the logical semes of the word semantics. These semes are consistent with the logical semes of the another word meanings, as a result, the given word demonstrates the combining capability with another word. This is considered to be its semantic valency. We have attempted to identify and investigate a peculiar kind of valency in the Kazakh language.

scholarly journals COMPATIBILITY OF LANGUAGE UNITS IN THE KAZAKH LANGUAGE AND THEIR CAPABILITY

2019 ◽  
pp. 36-39
Author(s):  
Amirbekova Aigul Baydebekkyzy ◽  
Khabiyeva Almagul ◽  
Soltanbekova Alfia ◽  
Taubaldiyev Meirambek
Keyword(s):  
Lexical Semantics ◽  
Broad Sense ◽  
Practical Significance ◽  
Word Meanings ◽  
Lexical Semantic ◽  
The Given

The article deals with the concept of valency as a phenomenon lying at the confluence of syntax and lexical semantics. The paper also represents types of valency, directions in which the theory of valency is considered. Valency in the broad sense of the word refers to the capacity of a language unit to enter into communication with other units of a particular order. Objectivity and scientific and practical significance of the theory of valency is determined by the lexical- semantic potential of the word. Semantic valency is based on the logical semes of the word semantics. These semes are consistent with the logical semes of the another word meanings, as a result, the given word demonstrates the combining capability with another word. This is considered to be its semantic valency. We have attempted to identify and investigate a peculiar kind of valency in the Kazakh language. We use the concepts of valency and compatibility as synonyms, but in a number of works they are distinguished.

Lexical Semantics of Russian Verbs and Their Function of Action Fixation Using Perfect Forms

2019 ◽  
Vol 80 (1) ◽  
pp. 81-87
Author(s):  
Sergei A. Karpukhin
Keyword(s):  
Lexical Semantics ◽  
Russian Language ◽  
New Approach ◽  
Lexical Semantic ◽  
Objective Time ◽  
Verb Forms ◽  
The Russian Language

This article describes the connection between perfect verb forms and the typical lexical meanings of generating imperfectives using the example of a prefix model in the Russian language. The research is based on a fundamentally new approach, i.e. the means of “fixing” action in the objective time. The relevance of combining the action and the situational background to the lexical-semantic groups of verbs is established. In the course of the research, the materials of the Bolshoi Akademichescky Slovar (Big Academic Dictionary) were used.

Wspólnota semantyczno-leksykalna języków europejskich. O monografii: А.А. Кретов, О.М. Воевудская, И.А. Меркулова, В.Т. Титов, Единство Европы по данным лексики (Воронеж: Издательский дом ВГУ, 2016, ss. 413 [1])

2018 ◽  
Vol 2 (XXIII) ◽  
pp. 121-133
Author(s):  
Katarzyna Wojan
Keyword(s):  
Comparative Research ◽  
Lexical Semantics ◽  
Research Field ◽  
Original Research ◽  
Linguistic Typology ◽  
Lexical Semantic ◽  
Theoretical Linguistics ◽  
Research Concept ◽  
New Research

This article outlines the original research concept developed and applied by the Voronezh researchers, which brought both quantitative and qualitative results to the field of linguistic comparative research. Their monograph is devoted to the macrotypological unity of the lexical semantics of the languages in Europe. In addition, semantic stratification of Russian and Polish lexis has been analyzed. Their research concept is now known as the “lexical-semantic macrotypological school of Voronezh.” Representatives of this school have created a new research field in theoretical linguistics – a lexical-semantic language macrotypology as a branch of linguistic typology. The monograph has been widely discussed and reviewed in Russia.

Time-Efficient Ensemble Learning with Sample Exchange for Edge Computing

2021 ◽  
Vol 21 (3) ◽  
pp. 1-17
Author(s):  
Wu Chen ◽  
Yong Yu ◽  
Keke Gai ◽  
Jiamou Liu ◽  
Kim-Kwang Raymond Choo
Keyword(s):  
Ensemble Learning ◽  
Real World ◽  
Interaction Mechanism ◽  
Training Model ◽  
Edge Computing ◽  
Learning Techniques ◽  
Multi Agent ◽  
Real World Datasets ◽  
Entire Dataset ◽  
Exchange Data

In existing ensemble learning algorithms (e.g., random forest), each base learner’s model needs the entire dataset for sampling and training. However, this may not be practical in many real-world applications, and it incurs additional computational costs. To achieve better efficiency, we propose a decentralized framework: Multi-Agent Ensemble. The framework leverages edge computing to facilitate ensemble learning techniques by focusing on the balancing of access restrictions (small sub-dataset) and accuracy enhancement. Specifically, network edge nodes (learners) are utilized to model classifications and predictions in our framework. Data is then distributed to multiple base learners who exchange data via an interaction mechanism to achieve improved prediction. The proposed approach relies on a training model rather than conventional centralized learning. Findings from the experimental evaluations using 20 real-world datasets suggest that Multi-Agent Ensemble outperforms other ensemble approaches in terms of accuracy even though the base learners require fewer samples (i.e., significant reduction in computation costs).

scholarly journals OFCOD: On the Fly Clustering Based Outlier Detection Framework

Data ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. 1
Author(s):  
Ahmed Elmogy ◽  
Hamada Rizk ◽  
Amany M. Sarhan
Keyword(s):  
Data Mining ◽  
Image Processing ◽  
Intrusion Detection ◽  
Real Time ◽  
Outlier Detection ◽  
Real World ◽  
Medical Data ◽  
Experimental Results ◽  
Real Time Applications ◽  
Real World Datasets

In data mining, outlier detection is a major challenge as it has an important role in many applications such as medical data, image processing, fraud detection, intrusion detection, and so forth. An extensive variety of clustering based approaches have been developed to detect outliers. However they are by nature time consuming which restrict their utilization with real-time applications. Furthermore, outlier detection requests are handled one at a time, which means that each request is initiated individually with a particular set of parameters. In this paper, the first clustering based outlier detection framework, (On the Fly Clustering Based Outlier Detection (OFCOD)) is presented. OFCOD enables analysts to effectively find out outliers on time with request even within huge datasets. The proposed framework has been tested and evaluated using two real world datasets with different features and applications; one with 699 records, and another with five millions records. The experimental results show that the performance of the proposed framework outperforms other existing approaches while considering several evaluation metrics.

scholarly journals Overlapping Community Detection Based on Attribute Augmented Graph

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 680
Author(s):  
Hanyang Lin ◽  
Yongzhao Zhan ◽  
Zizheng Zhao ◽  
Yuzhong Chen ◽  
Chen Dong
Keyword(s):  
Community Detection ◽  
Real World ◽  
Detection Algorithm ◽  
Overlapping Community Detection ◽  
Overlapping Communities ◽  
Adjustment Strategy ◽  
Topology Information ◽  
Overlapping Community ◽  
Real World Datasets ◽  
Community Detection Algorithm

There is a wealth of information in real-world social networks. In addition to the topology information, the vertices or edges of a social network often have attributes, with many of the overlapping vertices belonging to several communities simultaneously. It is challenging to fully utilize the additional attribute information to detect overlapping communities. In this paper, we first propose an overlapping community detection algorithm based on an augmented attribute graph. An improved weight adjustment strategy for attributes is embedded in the algorithm to help detect overlapping communities more accurately. Second, we enhance the algorithm to automatically determine the number of communities by a node-density-based fuzzy k-medoids process. Extensive experiments on both synthetic and real-world datasets demonstrate that the proposed algorithms can effectively detect overlapping communities with fewer parameters compared to the baseline methods.

Review Summary Generation in Online Systems: Frameworks for Supervised and Unsupervised Scenarios

2021 ◽  
Vol 15 (3) ◽  
pp. 1-33
Author(s):  
Wenjun Jiang ◽  
Jing Chen ◽  
Xiaofei Ding ◽  
Jie Wu ◽  
Jiawei He ◽  
...  
Keyword(s):  
Decision Making ◽  
Real World ◽  
Text Summarization ◽  
Experimental Results ◽  
Product Review ◽  
Comprehensive Review ◽  
Online Systems ◽  
Real World Datasets ◽  
Different Characteristics

In online systems, including e-commerce platforms, many users resort to the reviews or comments generated by previous consumers for decision making, while their time is limited to deal with many reviews. Therefore, a review summary, which contains all important features in user-generated reviews, is expected. In this article, we study “how to generate a comprehensive review summary from a large number of user-generated reviews.” This can be implemented by text summarization, which mainly has two types of extractive and abstractive approaches. Both of these approaches can deal with both supervised and unsupervised scenarios, but the former may generate redundant and incoherent summaries, while the latter can avoid redundancy but usually can only deal with short sequences. Moreover, both approaches may neglect the sentiment information. To address the above issues, we propose comprehensive Review Summary Generation frameworks to deal with the supervised and unsupervised scenarios. We design two different preprocess models of re-ranking and selecting to identify the important sentences while keeping users’ sentiment in the original reviews. These sentences can be further used to generate review summaries with text summarization methods. Experimental results in seven real-world datasets (Idebate, Rotten Tomatoes Amazon, Yelp, and three unlabelled product review datasets in Amazon) demonstrate that our work performs well in review summary generation. Moreover, the re-ranking and selecting models show different characteristics.

scholarly journals Multityped Community Discovery in Time-Evolving Heterogeneous Information Networks Based on Tensor Decomposition

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-16 ◽  
Author(s):  
Jibing Wu ◽  
Lianfei Yu ◽  
Qun Zhang ◽  
Peiteng Shi ◽  
Lihua Liu ◽  
...  
Keyword(s):  
Real World ◽  
Tensor Decomposition ◽  
Information Networks ◽  
Community Discovery ◽  
Star Network ◽  
Heterogeneous Information ◽  
Heterogeneous Information Networks ◽  
General Network ◽  
Real World Datasets ◽  
Discovery Method

The heterogeneous information networks are omnipresent in real-world applications, which consist of multiple types of objects with various rich semantic meaningful links among them. Community discovery is an effective method to extract the hidden structures in networks. Usually, heterogeneous information networks are time-evolving, whose objects and links are dynamic and varying gradually. In such time-evolving heterogeneous information networks, community discovery is a challenging topic and quite more difficult than that in traditional static homogeneous information networks. In contrast to communities in traditional approaches, which only contain one type of objects and links, communities in heterogeneous information networks contain multiple types of dynamic objects and links. Recently, some studies focus on dynamic heterogeneous information networks and achieve some satisfactory results. However, they assume that heterogeneous information networks usually follow some simple schemas, such as bityped network and star network schema. In this paper, we propose a multityped community discovery method for time-evolving heterogeneous information networks with general network schemas. A tensor decomposition framework, which integrates tensor CP factorization with a temporal evolution regularization term, is designed to model the multityped communities and address their evolution. Experimental results on both synthetic and real-world datasets demonstrate the efficiency of our framework.

scholarly journals Dimension Reduction for Objects Composed of Vector Sets

2017 ◽  
Vol 27 (1) ◽  
pp. 169-180 ◽  
Author(s):  
Marton Szemenyei ◽  
Ferenc Vajda
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Feature Selection ◽  
Discriminant Analysis ◽  
Probability Distribution ◽  
Dimension Reduction ◽  
Pose Estimation ◽  
Real World ◽  
Single Object ◽  
Real World Datasets

Abstract Dimension reduction and feature selection are fundamental tools for machine learning and data mining. Most existing methods, however, assume that objects are represented by a single vectorial descriptor. In reality, some description methods assign unordered sets or graphs of vectors to a single object, where each vector is assumed to have the same number of dimensions, but is drawn from a different probability distribution. Moreover, some applications (such as pose estimation) may require the recognition of individual vectors (nodes) of an object. In such cases it is essential that the nodes within a single object remain distinguishable after dimension reduction. In this paper we propose new discriminant analysis methods that are able to satisfy two criteria at the same time: separating between classes and between the nodes of an object instance. We analyze and evaluate our methods on several different synthetic and real-world datasets.

Sign in / Sign up

Export Citation Format

Share Document