The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We proposed neural network architecture based on Convolution Neural Network(CNN) for temporal relation classification in sentence. First, we transformed word into vector by using word embedding. In Feature Extraction, we extracted two type of features. Lexical level feature considered meaning of marked entity and Sentence level feature considered context of the sentence. Window processing was used...
This paper describes performance of an interpreter uncovering meanings of prepositions in "master" — preposition — "slave" constructions. The basis of the semantic interpreter is a set of "if A, than B" rules, with the left parts containing lexical and semantic markers of the "masters" and the "slaves" and morphological markers of the "slaves"...
Mediation is an approach that allows integrating different heterogeneous, distributed and scalable data sources. The objective of our paper is to define an approach of mapping, one of the essential operations that can describe and define the set of links between the two levels of mediation system: mediator schema (global) and schemas of sources to be integrated (local). Our approach allows to define...
This paper presents a case study of discovering and classifying verbs in large web-corpora. Many tasks in natural language processing require corpora containing billions of words, and with such volumes of data co-occurrence extraction becomes one of the performance bottlenecks in the Vector Space Models of computational linguistics. We propose a co-occurrence extraction kernel based on ternary trees...
With ever growing data on Internet, use of search engines has increased tremendously to find information. It is experienced that current search engines give many irrelevant and redundant results for a query. Redundancy and irrelevance can be reduced by using user intent based context while composing a search string query. This research proposes an algorithm to improve the prediction of search string...
In this paper, we present a method of grammatical and semantic disambiguation of the particle or the token "hattā" in Arabic language. This method is based on a thorough analysis of the context. Our goal is to achieve the maximum linguistic information of this token thanks to a corpus in order to modeling as a grammar or rules. To do this, we first developed a corpus that contains the different...
This work falls within the framework of the Natural Language Processing. Its objective is to assess the level of ambiguity caused by the absence of diacritical marks in Arabic texts during the information extraction process. We have carried out a statistical study based on four indicators: the root, the lemma, the stem and the POS tag of the word. For this, we used a large vowelized corpus containing...
This paper proposes an approach to translating a use case diagram into an executable context-aware ambients. The requirements of a context-aware system is captured and represented in an extension of UML use case diagrams called context-aware use case diagrams. Then an algorithm is proposed that translates a context-aware use case diagram into a process in the Calculus of Context-aware Ambients (CCA)...
With the rise of the services-based economy and the democratization of on-line services, more and more users (individual and/or business) use on-line applications in their daily lives. Usually personal data transits between different actors involved in a service's delivery chain (e.g. application/storage service providers) and thus might raise some privacy issues. Accountability, which is the property...
Collaboration patterns are an efficient way to define, reuse and enact collaborative software development processes. We propose an approach to define and apply collaboration patterns at modelling, instantiation or execution time. Our patterns, inspired from workflow patterns, are described in CMSPEM, a Process Modelling Language developed in our team. In this paper, we briefly describe the CMSPEM...
The Object Constraint Language (OCL) is commonly used for constraints in meta-model-based language specifications. However, it may be advantageous to have a domain-specific constraint meta-language optimised for language specifications. A survey of OCL usage in language specifications has been performed, in order to gain an understanding of common constraint patterns. This is used as a starting point...
This paper proposes a CABAC decoder for HEVC that achieves constant high throughput multi-bin decoding with the parallel syntax element parser to solve the dependency problem in the traditional prediction based multi-bin architecture. The hardware implementation with TSMC 90nm CMOS technology can process 1 bins per cycles with 48,430 gate count (270Mbins/sec,) or 3 bins per cycle with 209,422 gate...
In this paper, we focus on the exception handling mechanism of CA-CCML (Context-aware Cooperative Composition Modeling Language). First, according to level of exception generation, we divide Web service exceptions into three broad categories by levels of exception generation, which are Service invocation level exception, Syntax level exception and Semantic level exception. Then we make detail classification...
Software developers often need to transfer func-tionality, e.g., a set of commits implementing a new feature or a bug fix, from one branch of a configuration management system to another. That can be a challenging task as the existing configuration management tools lack support for matching high-level semantic functionality with low-level version histories. The developer thus has to either manually...
Recently, the NLP community has shown a renewed interest in lexical semantics in the extent of automatic recognition of semantic relationships between pairs of words in text. Lexical semantics has become increasingly important in many natural language applications, this approach to semantics is concerned with psychological facts associated with meaning of words and how these words can be connected...
A key question in sentiment analysis is whether sentiment ex-pressions, in a given text, are related to particular entities. This is an imperative question, since people are typically interested in sentiments on specific entities and not in the overall sentiment articulated in an article or a document. Sentiment relevance is aimed at addressing this precise problem. In this paper, we argue that exploiting...
CABAC is high-compression-ratio entropy coding in HEVC, but it is difficult to be parallelized for speedup. In this paper, a pipelined HEVC CABAC architecture is proposed to increase operating frequency. The proposed CABAC encoder was implemented in 0.18um technology with 158 MHz operating frequency and 45,088 gate counts.
Hindi is the fourth largest spoken language in the world. Nowadays in India, working on Internet using Hindi language is becoming popular. But Hindi language has several ambiguous words which affect on sense of the Hindi sentence. The word "Ambiguous" refers to "having more than one meaning or senses". The technique of examining the correct meaning of a word as specified in a given...
We introduce the principles of symbolization and conceptualization of perceived reality. We show them as processes that are applicable inside of a computer mind. We derive those processes from principles of a human mind. We present process of higher order regular abstraction and state automata acceptance as possible machine reality realization mechanism. We present the algorithm for evolution of machine...
The term Projectional editor is commonly used for tools that can work directly with the program's abstract syntax tree. They are able to provide different views of the program, according to the specific editor used. The ability to look at the program from multiple views is often requested as a mean to simplify program comprehension. During their evolution, the Integrated Development Environments were...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.