Language-independent Model Research Articles

Graph transformer for cross-lingual plagiarism detection

<span lang="EN-US">The existence of vast amounts of multilingual textual data on the internet leads to cross-lingual plagiarism which becomes a serious issue in different fields such as education, science, and literature. Current cross-lingual plagiarism detection approaches usually employ syntactic and lexical properties, external machine translation systems, or finding similarities within a multilingual set of text documents. However, most of these methods are conceived for literal plagiarism such as copy and paste, and their performance is diminished when handling complex cases of plagiarism including paraphrasing. In this paper, we propose a new graph-based approach that represents text passages in different languages using knowledge graphs. We put forward a new graph structure modeling method based on the Transformer architecture that employs precise relation encoding and delivers a more efficient way for global graph representation. The mappings between the graphs are learned both in semi-supervised and unsupervised training mechanisms. The results of our experiments in Arabic–English, French–English, and Spanish–English plagiarism detection show that our graph transformer method surpasses the state-of-the-art cross-lingual plagiarism detection approaches with and without paraphrasing cases, and provides further insights on the use of knowledge graphs on a language-independent model.</span>

Frustration Level in Customer Support Tweets: Towards a Language-Independent Model

Frustration Level in Customer Support Tweets: Towards a Language-Independent Model

Multilingual handwritten numeral recognition using a robust deep network joint with transfer learning

Numeral recognition plays a crucial role in creating automated systems such as posting address sorting and license plate recognition. Nowadays, numeral recognition systems which have the capability of recognising multiple languages are highly beneficial due to growing international correspondence and transactions, especially in multilingual countries where several languages are used simultaneously. Therefore, handwritten numeral recognition is more challenging than printed numeral recognition due to having different and complex handwriting styles. Hence, developing a multilingual handwritten system is considered as an important and debatable issue. We address this issue by proposing a language-independent model based on a robust CNN. Our proposed model is composed of language recognition and digit recognition, which aims to handle the recognition of multi-script images. We used transfer-learning in the proposed system to enhance the image quality and consequently the recognition performance. Extensive experiments were conducted to verify the effectiveness of both language and digit recognition procedures. The proposed system was tested with six different languages. The results showed an average accuracy of up to 99.8% for recognising various languages and the associated digits. The robustness and design procedure of the proposed model created a cost-effective extension for recognition of handwritten numerals in other languages.

A system for detection of moving caption text in videos: a news use case

Extraction of news text captions aims at a digital understanding of what is happening in a specific region during a certain period that helps in better communication between different nations because we can easily translate the plain text from one language to another. Moving text captions causes blurry effects that are a significant cause of text quality impairments in the news channels. Most of the existing text caption detection models do not address this problem in a way that captures the different dynamic motion of captions, gathers a full news story among several frames in the sequence, resolves the blurring effect of text motion, offers a language-independent model, or provides it as an end-to-end solution for the community to use. We process the frames coming in sequence and extract edge features using either the Hough transform or our color-based technique. We verify text existence using a Convolutional Neural Network (CNN) text detection pre-trained model. We analyze the caption motion status using hybrid pre-trained Recurrent Neural Network (RNN) of Long Short-Term Memory (LSTM) type model and correlation-based model. In case the motion is determined to be horizontal rotation, there are two problems. First, it means that text keeps rotating with no stop resulting in a high blurring effect that affects the text quality and consequently resulting in low character recognition accuracy. Second, there are successive news stories which are separated by the channel logo or long spaces. We managed to solve the first problem by deblurring the text image using either Bicubic Spline Interpolation (BSI) technique or the Denoising Autoencoder Neural Network (DANN). We solved the second problem using a Point Feature Matching (PFM) technique to match the existing channel logo with the channels’ logo database (ground truth). We evaluate our framework using Abbyy® SDK as a standalone tool used for text recognition supporting different languages.

A Lightweight Approach to the Multi-perspective Modeling of Processes and Objects

Abstract Process modeling has a broad range of applications, varying from business and system engineering, via artifact design, up to natural process modeling utilized in natural sciences. Over the last decades, various sophisticated languages and frameworks have been developed to support process modeling. The current paper discusses an approach to process modeling, which is, in contrast to many existing solutions, intended for the integrated process and object modeling. Furthermore, it is designed to be a lightweight approach with only a few constructs, which, however, permit the representation of processes from various perspectives. The developed solution provides an abstract language-independent model (ontology), partial formalization in first-order logic as well as a Web Ontology Language (OWL) implementation.

An Ontology-Based Product Architecture Derivation Approach

Software product line (SPL) engineering has proven to improve software quality and shorten development cycles, cost and time. In product line engineering, product derivation is concerned with the realization of the variability at the implementation level. However, the majority of research works focuses on instantiating the variants selected in the final product, while the derivation at the architecture level has been poorly explored. As product line engineers often customize the product architecture by hand during the application engineering phase, the derivation and customization processes of the product line architecture (PLA) might be in some cases error-prone. Consequently, in this research we present an Ontology-based product Architecture Derivation (OntoAD) framework which automates the derivation of product-specific architectures from an SPL architecture. Our solution uses a language-independent model to specify the product line architecture and a model-driven engineering approach for architecture derivation activities. We use an ontology formalism to reason about the automatic generation of model-to-model transformation rules based on the selection of features and we illustrate our approach using a voice over IP motivating example. Finally, we report results about scalability and performance regarding the size of the variability model.

Termination of nondeterministic quantum programs

We define a language-independent model of nondeterministic quantum programs in which a quantum program consists of a finite set of quantum processes. These processes are represented by quantum Markov chains over the common state space, which formalize the quantum mechanical behaviors of the machine. An execution of a nondeterministic quantum program is modeled by a sequence of actions of individual processes, and at each step of an execution a process is chosen nondeterministically to perform the next action. This execution model formalize the users’ behavior of calling the processes in the classical world. Applying the model to a quantum walk as an instance of physically realizable systems, we describe an execution step by step. A characterization of reachable space and a characterization of diverging states of a nondeterministic quantum program are presented. We establish a zero-one law for termination probability of the states in the reachable space. A combination of these results leads to a necessary and sufficient condition for termination of nondeterministic quantum programs. Based on this condition, an algorithm is found for checking termination of nondeterministic quantum programs within a fixed finite-dimensional state space.

Interoperability of remote handling control system software modules at Divertor Test Platform 2 using middleware

This paper focuses on the inter-subsystem communication channels in a prototype distributed remote handling control system at Divertor Test Platform 2 (DTP2). The subsystems are responsible for specific tasks and, over the years, their development has been carried out using various platforms and programming languages. The communication channels between subsystems have different priorities, e.g. very high messaging rate and deterministic timing or high reliability in terms of individual messages.Generally, a control system's communication infrastructure should provide interoperability, scalability, performance and maintainability. An attractive approach to accomplish this is to use a standardized and proven middleware implementation. The selection of a middleware can have a major cost impact in future integration efforts.In this paper we present development done at DTP2 using the Object Management Group's (OMG) standard specification for Data Distribution Service (DDS) for ensuring communications interoperability. DDS has gained a stable foothold especially in the military field. It lacks a centralized broker, thereby avoiding a single-point-of-failure. It also includes an extensive set of Quality of Service (QoS) policies. The standard defines a platform- and programming language independent model and an interoperability wire protocol that enables DDS vendor interoperability, allowing software developers to avoid vendor lock-in situations.

Language-Independent and Automated Software Composition: The FeatureHouse Experience

Superimposition is a composition technique that has been applied successfully in many areas of software development. Although superimposition is a general-purpose concept, it has been (re)invented and implemented individually for various kinds of software artifacts. We unify languages and tools that rely on superimposition by using the language-independent model of feature structure trees (FSTs). On the basis of the FST model, we propose a general approach to the composition of software artifacts written in different languages. Furthermore, we offer a supporting framework and tool chain, called FEATUREHOUSE. We use attribute grammars to automate the integration of additional languages. In particular, we have integrated Java, C#, C, Haskell, Alloy, and JavaCC. A substantial number of case studies demonstrate the practicality and scalability of our approach and reveal insights into the properties that a language must have in order to be ready for superimposition. We discuss perspectives of our approach and demonstrate how we extended FEATUREHOUSE with support for XML languages (in particular, XHTML, XMI/UML, and Ant) and alternative composition approaches (in particular, aspect weaving). Rounding off our previous work, we provide here a holistic view of the FEATUREHOUSE approach based on rich experience with numerous languages and case studies and reflections on several years of research.

A formal model for the interoperability of service clouds

Large-scale service-oriented computing is based on the idea that services from various servers are combined into one distributed application. Referring to a collection of services on one server as a “service cloud”, the problem investigated in this paper is to define formal high-level specifications of such distributed applications and to enable the location of suitable services for them. Based on the language-independent model of Abstract State Services (AS2s), which serves as a universal integrated model for data and software as services, we extend AS2s by high-level action schemes called “plots” as a means to specify permitted sequences of service operations. On these grounds, we develop a model for service mediators, that is, specifications of composed services in which service slots have to be filled by actual services, and investigate matching conditions for slots of mediators and services. For a services to match a slot in a mediator, a (generalised) projection of the mediator must comply with the plot of the service. Furthermore, the service must be semantically adequate, which requires the use of a service ontology.

SINAI experience at CLEF

This paper reports our work on CLEF and CrossLanguage Information Retrieval using CLEF resources. We aim to construct a highly languageindependent CLIR model. To accomplish this objective, several problems must be overcome: text translation or pseudo-translation and merging the obtained results for each language for a given query. Three issues of text-translation are investigated: the impact of translation probabilities, automatic multi-word recognition, and the generation of similarity thesauri from a Web corpus. Because the proposed model is query-translation driven, it is necessary to merge several monolingual results in a unique multilingual list of documents. To accomplish this task, we propose a new approach, which we call 2-step RSV, and we show that it performs better than more traditional approaches.

GALEN: a third generation terminology tool to support a multipurpose national coding system for surgical procedures

Generalised architecture for languages, encyclopaedias and nomenclatures in medicine (GALEN) has developed a new generation of terminology tools based on a language independent model describing the semantics and allowing computer processing and multiple reuses as well as natural language understanding systems applications to facilitate the sharing and maintaining of consistent medical knowledge. During the European Union 4 Th. framework program project GALEN-IN-USE and later on within two contracts with the national health authorities we applied the modelling and the tools to the development of a new multipurpose coding system for surgical procedures named CCAM in a minority language country, France. On one hand, we contributed to a language independent knowledge repository and multilingual semantic dictionaries for multicultural Europe. On the other hand, we support the traditional process for creating a new coding system in medicine which is very much labour consuming by artificial intelligence tools using a medically oriented recursive ontology and natural language processing. We used an integrated software named CLAW (for classification workbench) to process French professional medical language rubrics produced by the national colleges of surgeons domain experts into intermediate dissections and to the Grail reference ontology model representation. From this language independent concept model representation, on one hand, we generate with the LNAT natural language generator controlled French natural language to support the finalisation of the linguistic labels (first generation) in relation with the meanings of the conceptual system structure. On the other hand, the Claw classification manager proves to be very powerful to retrieve the initial domain experts rubrics list with different categories of concepts (second generation) within a semantic structured representation (third generation) bridge to the electronic patient record detailed terminology.

Development of Engineering Software Within a Generic Application Framework

This paper shows that object‐oriented generic application frameworks can be used to improve the design and implementation of interactive engineering software. Enhanced development time, consistency, transparency, flexibility, and quality are achieved by separating programs into generic and domain‐specific components. Advantages of object‐oriented programming over conventional procedure‐oriented approaches are highlighted for the development of basic interactive software (event‐driven architectures, user‐interface standards, etc.). A language‐independent model is used to provide the implementation details for a generic application framework called “GenApp.” Programs can be constructed on top of this framework by creating specialized object classes that selectively mix inherited generic behavior with application‐specific tasks. Customized user‐interface, object management, and support for existing procedures are some of the features offered by GenApp to simplify the development of engineering software. A finite‐element analysis program is shown as an example product of this generic application framework.

Generating editing environments based on relations and attributes

The ability to generate language-based editors depends on the existence of a powerful, language-independent model of editing. A model is proposed in which programs are represented as attributed abstract-syntax trees with an associated relational database. Relations can depend on the state of the attributed tree, and attributes can depend on the values in relations, provided there are no circular dependencies. The power and the limitations of relational operations are demonstrated with respect to the support of static-semantic checking, anomaly detection, an interrogation facility, and the ability to define alternative program displays. The advantages of the hybrid system over both the purely relational and purely attribute-based systems are presented, and new algorithms are given for query evaluation and incremental view updating motivated by the efficiency requirements of interactive editing under the defined model. A prototype implementation of an editor generator is described, and suggestions for future research are made.

Relations and attributes

The ability to generate language-based editors depends on the existence of a powerful, language-independent model of editing. A model is proposed in which programs are represented as attributed abstract-syntax trees with an associated relational database. Relations can depend on the state of the attributed tree, and attributes can depend on the values in relations, provided there are no circular dependencies. The power and the limitations of relational operations are demonstrated with respect to the support of static-semantic checking, anomaly detection, an interrogation facility, and the ability to define alternate views of a program. The advantages of the hybrid system over both the purely relational and purely attribute-based systems are presented, and a prototype implementation of an editor generator is discussed. New algorithms are given for query evaluation and incremental view updating motivated by the efficiency requirements of interactive editing under the defined model.

Relations and attributes

The ability to generate language-based editors depends on the existence of a powerful, language-independent model of editing. A model is proposed in which programs are represented as attributed abstract-syntax trees with an associated relational database. Relations can depend on the state of the attributed tree, and attributes can depend on the values in relations, provided there are no circular dependencies.