The knowledge acquisition bottleneck problem, well-known to the Knowledge Management community, is turning the weaving of the Semantic Web (SW) into a hard and slow process. Nowadays' high costs associated with producing two versions of a document – one version for human consumption and another version for machine consumption – prevent the creation of enough metadata to make the SW realizable. ...

The search tools and information retrieval systems on the contemporary Web use keywords, lexical analysis, popularity, and statistical methods to find and prioritise relevant data to a specific query. In recent years, Semantic web has introduced new approaches to specify Web data using machine-interpretable structures. This has led to the establishment of new frameworks for search engines and i...

This study proposes to employ syntactic and semantic knowledge from the rich relations within a tree kernel structure for relation extraction. The underlying idea is that different tree kernels with a variety of representations of the available linguistic information will improve the performance of detecting useful pieces of information expressed in a sentence. Applying clause-based rules, clus...

We develop a semantic parsing framework based on semantic similarity for open domain question answering (QA). We focus on single-relation questions and decompose each question into an entity mention and a relation pattern. Using convolutional neural network models, we measure the similarity of entity mentions with entities in the knowledge base (KB) and the similarity of relation patterns and r...

In this paper, we observe that there exists a second dimension to the relation extraction (RE) problem that is orthogonal to the relation type dimension. We show that most of these second dimensional structures are relatively constrained and not difficult to identify. We propose a novel algorithmic approach to RE that starts by first identifying these structures and then, within these, identify...

This paper describes the development of a prototype system to answer questions by selecting sentences from the documents in which the answers occur. After parsing each sentence in these documents, databases are constructed by extracting relational triples from the parse output. The triples consist of discourse entities, semantic relations, and the governing words to which the entities are bound...

Information Extraction (IE) is a technology for localizing and classifying pieces of relevant information in unstructured natural language texts and detecting relevant relations among them. This thesis deals with one of the central tasks of IE, i.e., relation extraction. The goal is to provide a general framework that automatically learns mappings between linguistic analyses and target semantic...

We present an approach for semantic relation extraction between nominals that combines semantic information with shallow syntactic processing. We propose to use the ResearchCyc knowledge base as a source of semantic information about nominals. Each source of information is represented by a specific kernel function. The experiments were carried out using support vector machines as a classifier. ...

Recognizing semantic relations between sentences, such as entailment and contradiction, is a challenging task that requires detailed analysis of the interaction between diverse linguistic phenomena. In this paper, we propose a latent discriminative model that unifies a statistical framework and a theory of Natural Logic to capture complex interactions between linguistic phenomena. The proposed ...

State-of-the-art bootstrapping systems rely on expert-crafted semantic constraints such as negative categories to reduce semantic drift. Unfortunately, their use introduces a substantial amount of supervised knowledge. We present the Relation Guided Bootstrapping (RGB) algorithm, which simultaneously extracts lexicons and open relationships to guide lexicon growth and reduce semantic drift. Thi...