arXiv subjects

Mohammad-Reza Feizi-Derakhshi

Publications and source records attributed to Mohammad-Reza Feizi-Derakhshi.

25 records · Page 2Linked to original sources

arXiv2021

Phraseformer: Multimodal Key-phrase Extraction using Transformer and Graph Embedding

Background: Keyword extraction is a popular research topic in the field of natural language processing. Keywords are terms that describe the most relevant information in a document. The main problem that researchers are facing is how to efficiently and accurately extract the core keywords from a document. However, previous keyword extraction approaches have utilized the text and graph features, there is the lack of models that can properly learn and combine these features in a best way. Methods: In this paper, we develop a multimodal Key-phrase extraction approach, namely Phraseformer, using transformer and graph embedding techniques. In Phraseformer, each keyword candidate is presented by a vector which is the concatenation of the text and structure learning representations. Phraseformer takes the advantages of recent researches such as BERT and ExEm to preserve both representations. Also, the Phraseformer treats the key-phrase extraction task as a sequence labeling problem solved using classification task. Results: We analyze the performance of Phraseformer on three datasets including Inspec, SemEval2010 and SemEval 2017 by F1-score. Also, we investigate the performance of different classifiers on Phraseformer method over Inspec dataset. Experimental results demonstrate the effectiveness of Phraseformer method over the three datasets used. Additionally, the Random Forest classifier gain the highest F1-score among all classifiers. Conclusions: Due to the fact that the combination of BERT and ExEm is more meaningful and can better represent the semantic of words. Hence, Phraseformer significantly outperforms single-modality methods.

cs.CL↗

arXiv2020

TopicBERT: A Transformer transfer learning based memory-graph approach for multimodal streaming social media topic detection

Real time nature of social networks with bursty short messages and their respective large data scale spread among vast variety of topics are research interest of many researchers. These properties of social networks which are known as 5'Vs of big data has led to many unique and enlightenment algorithms and techniques applied to large social networking datasets and data streams. Many of these researches are based on detection and tracking of hot topics and trending social media events that help revealing many unanswered questions. These algorithms and in some cases software products mostly rely on the nature of the language itself. Although, other techniques such as unsupervised data mining methods are language independent but many requirements for a comprehensive solution are not met. Many research issues such as noisy sentences that adverse grammar and new online user invented words are challenging maintenance of a good social network topic detection and tracking methodology; The semantic relationship between words and in most cases, synonyms are also ignored by many of these researches. In this research, we use Transformers combined with an incremental community detection algorithm. Transformer in one hand, provides the semantic relation between words in different contexts. On the other hand, the proposed graph mining technique enhances the resulting topics with aid of simple structural rules. Named entity recognition from multimodal data, image and text, labels the named entities with entity type and the extracted topics are tuned using them. All operations of proposed system has been applied with big social data perspective under NoSQL technologies. In order to present a working and systematic solution, we combined MongoDB with Neo4j as two major database systems of our work. The proposed system shows higher precision and recall compared to other methods in three different datasets.

cs.CL↗

arXiv2020

A Speech Act Classifier for Persian Texts and its Application in Identifying Rumors

Speech Acts (SAs) are one of the important areas of pragmatics, which give us a better understanding of the state of mind of the people and convey an intended language function. Knowledge of the SA of a text can be helpful in analyzing that text in natural language processing applications. This study presents a dictionary-based statistical technique for Persian SA recognition. The proposed technique classifies a text into seven classes of SA based on four criteria: lexical, syntactic, semantic, and surface features. WordNet as the tool for extracting synonym and enriching features dictionary is utilized. To evaluate the proposed technique, we utilized four classification methods including Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), and K-Nearest Neighbors (KNN). The experimental results demonstrate that the proposed method using RF and SVM as the best classifiers achieved a state-of-the-art performance with an accuracy of 0.95 for classification of Persian SAs. Our original vision of this work is introducing an application of SA recognition on social media content, especially the common SA in rumors. Therefore, the proposed system utilized to determine the common SAs in rumors. The results showed that Persian rumors are often expressed in three SA classes including narrative, question, and threat, and in some cases with the request SA.

cs.CL↗

arXiv2014

An improved multimodal PSO method based on electrostatic interaction using n- nearest-neighbor local search

In this paper, an improved multimodal optimization (MMO) algorithm,called LSEPSO,has been proposed. LSEPSO combined Electrostatic Particle Swarm Optimization (EPSO) algorithm and a local search method and then made some modification on them. It has been shown to improve global and local optima finding ability of the algorithm. This algorithm useda modified local search to improve particle's personal best, which used n-nearest-neighbour instead of nearest-neighbour. Then, by creating n new points among each particle and n nearest particles, it tried to find a point which could be the alternative of particle's personal best. This method prevented particle's attenuation and following a specific particle by its neighbours. The performed tests on a number of benchmark functions clearly demonstrated that the improved algorithm is able to solve MMO problems and outperform other tested algorithms in this article.

cs.AI↗

arXiv2013

Double four-bar crank-slider mechanism dynamic balancing by meta-heuristic algorithms

In this paper, a new method for dynamic balancing of double four-bar crank slider mechanism by meta- heuristic-based optimization algorithms is proposed. For this purpose, a proper objective function which is necessary for balancing of this mechanism and corresponding constraints has been obtained by dynamic modeling of the mechanism. Then PSO, ABC, BGA and HGAPSO algorithms have been applied for minimizing the defined cost function in optimization step. The optimization results have been studied completely by extracting the cost function, fitness, convergence speed and runtime values of applied algorithms. It has been shown that PSO and ABC are more efficient than BGA and HGAPSO in terms of convergence speed and result quality. Also, a laboratory scale experimental doublefour-bar crank-slider mechanism was provided for validating the proposed balancing method practically.

cs.AI↗

arXiv2011

Proposing Cluster_Similarity Method in Order to Find as Much Better Similarities in Databases

Different ways of entering data into databases result in duplicate records that cause increasing of databases' size. This is a fact that we cannot ignore it easily. There are several methods that are used for this purpose. In this paper, we have tried to increase the accuracy of operations by using cluster similarity instead of direct similarity of fields. So that clustering is done on fields of database and according to accomplished clustering on fields, similarity degree of records is obtained. In this method by using present information in database, more logical similarity is obtained for deficient information that in general, the method of cluster similarity could improve operations 24% compared with previous methods.

cs.DB↗

arXiv2010

Proposing a New Method for Query Processing Adaption in DataBase

This paper proposes a multi agent system by compiling two technologies, query processing optimization and agents which contains features of personalized queries and adaption with changing of requirements. This system uses a new algorithm based on modeling of users' long-term requirements and also GA to gather users' query data. Experimented Result shows more adaption capability for presented algorithm in comparison with classic algorithms.

cs.DB↗