ABSTRACT Automatically discovering semantic links among documents is the basis of developing advanced applications on large-scale documentary resources. This paper proposes an approach to automatically discover semantic links in a given document set. It has the following advantages: (1) It does not rely on any predefined ontology. (2) The semantic link networks and relevant rules automatically ...

In the current paper we describe how to combine web services and task patterns in a joint infrastructure. The central intention is to make up executable business processes by including generic pattern based web services which establish a relation between the service infrastructure and task management. This approach significantly increases the flexibility of process modeling due to the flexible ...

The Many Using and Creating Hypermedia (MUCH) system is based on the Dexter model and treats the storage layer as a semantic net. The MUCH system provides a number of recommended link types for representing application domain concepts, such as thesauri, documents, and annotations. Users of the system are expected to use those link types in the course of authoring meaningful hypermedia. This pap...

This paper presents a new method for extracting meaningful relations from unstructured natural language sources. The method is based on information made available by shallow semantic parsers. Semantic information was used (1) to enhance a dependency tree kernel; and (2) to build semantic dependency structures used for enhanced relation extraction for several semantic classifiers. In our experim...

This paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence. We investigate two typical and well-studied tasks: semantic role labeling (SRL) which identifies the relations between predicates and arguments, and relation classification (RC) which focuses on the relation between two entities or nominals. While mostly...

Semantic relation extraction is a meaningful task in NLP that could provide some helpful information and semantic relation classification attracts many people to research it. This paper mainly introduces a Bi-direction LSTM (long short-term memory) deep neutral network and the parameter of embedding layer, and this network can solve the problem of over-fitting. And then according to the text of...

Relation extraction is one of the important research topics in the field of information extraction research. To solve the problem of semantic variation in traditional semisupervised relation extraction algorithm, this paper proposes a novel semisupervised relation extraction algorithm based on ensemble learning (LXRE). The new algorithm mainly uses two kinds of support vector machine classifier...

Abstract. This paper presents the extension of an existing mimimally supervised rule acquisition method for relation extraction by coreference resolution (CR). To this end, a novel approach to CR was designed and tested. In comparison to state-of-the-art methods for CR, our strategy is driven by the target semantic relation and utilizes domain-specific ontological and lexical knowledge in addit...

We propose in this paper to use NLP approaches to validate induced syntactic relations. We focus on a Web Validation system, a Semantic Vector-based approach, and finally a Combined system. The Semantic Vector approach is a Rogetbased approach which computes a syntactic relation as a vector. The Web Validation technique uses a search engine to determine the relevance of a syntactic relation. We...

Semantic research is generally divided into lexical semantics (LS) and compositional semantics (CS). LS concentrates on the relation between a semantic functor and its arguments, be it in terms of semantic selectional restrictions or in terms of linking, i.e., in terms of the relation between syntactic complements and semantic argument slots. CS is concerned with the way the semantic contributi...