Search results for "Natural Language Processing"

Above the Sentence Level

2021

Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier

2020

Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses \emph{interpretable} open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clau…

The visual query language CQL for transitive and relational computation

2000

Abstract Classification query language (CQL) is a high-level visual query language with a great expressive power. In CQL the processing of ordinary relations and classifications based on transitive relationships is integrated seamlessly. Relations and classifications are represented in the visual interface in a uniform way through relation and classification skeletons. All query formulation in CQL is QBE-like – based on the intuitive way of filling constants and sample values into the skeletons. In order to guarantee great expressive power, relational and classification expressions can be nested freely with each other at unlimited nesting levels. Recursive definition of transitive processin…

Wordnet and semidiscrete decomposition for sub-symbolic representation of words

2009

A methodology for sub-symbolic semantic encoding of words is presented. The methodology uses the standard, semantically highly-structured WordNet lexical database and the SemiDiscrete matrix Decomposition to obtain a vector representation with low memory requirements in a semantic n-space. The application of the proposed algorithm over all the WordNet words would lead to a useful tool for the sub-symbolic processing of texts.

A Novel Approach to Improve the Accuracy of Web Retrieval

2010

General purpose search engines utilize a very simple view on text documents: They consider them as bags of words. It results that after indexing, the semantics of documents is lost. In this paper, we introduce a novel approach to improve the accuracy of Web retrieval. We utilize the WordNet and WordNet SenseRelate All Words Software as main tools to preserve the semantics of the sentences of documents and user queries. Nouns and verbs in the WordNet are organized in the tree hierarchies. The word meanings are presented by numbers that reference to the nodes on the semantic tree. The meaning of each word in the sentence is calculated when the sentence is analyzed. The goal is to put each nou…

Extracting Semantic Knowledge from Unstructured Text Using Embedded Controlled Language

2016

Nowadays, most of the data on the Web is still in the form of unstructured text. Knowledge extraction from unstructured text is highly desirable but extremely challenging due to the inherent ambiguity of natural language. In this article, we present an architecture of an information extraction system based on the concept of Embedded Controlled Language that allows for extracting formal semantic knowledge from an unstructured text corpus. Moreover, the presented approach has a potential to support multilingual input and output.

Semantic retrieval: an approach to representing, searching and summarising text documents

2011

Nowadays, the internet is the major source of information for millions of people. There are many search tools available on the net but finding appropriate text information is still difficult. The retrieval efficiency of the presently used systems cannot be significantly improved: ‘bag of words’ interpretation causes losing semantics of texts. We applied the functional approach to represent English text documents. It allows taking into account semantic relations between words when indexing documents and use ordinary English sentences as queries to a search engine. The proposed retrieval mechanisms return only highly relevant documents. They make it possible to generate content-aware summarie…

A Semantic Layer on Semi-structured Data Sources for Intuitive Chatbots

2009

The main limits of chatbot technology are related to the building of their knowledge representation and to their rigid information retrieval and dialogue capabilities, usually based on simple "pattern matching rules". The analysis of distributional properties of words in a texts corpus allows the creation of semantic spaces where represent and compare natural language elements. This space can be interpreted as a "conceptual" space where the axes represent the latent primitive concepts of the analyzed corpus. The presented work aims at exploiting the properties of a data-driven semantic/conceptual space built using semi-structured data sources freely available on the web, like Wikipedia. Thi…

A Comparison of Language Identification Approaches on Short, Query-Style Texts

2010

In a multi-language Information Retrieval setting, the knowledge about the language of a user query is important for further processing. Hence, we compare the performance of some typical approaches for language detection on very short, query-style texts. The results show that already for single words an accuracy of more than 80% can be achieved, for slightly longer texts we even observed accuracy values close to 100%.

Enriching Didactic Similarity Measures of Concept Maps by a Deep Learning Based Approach

2021

Concept maps are significant tools able to support several tasks in the educational area such as curriculum design, knowledge organization and modeling, students' assessment and many others. They are also successfully used in learning activities in which students have to represent domain knowledge according to teacher's assignment. In this context, the development of Learning Analytics approaches would benefit of methods that automatically compare concept maps. Detecting concept maps similarities is relevant to identify how the same concepts are used in different knowledge representations. Algorithms for comparing graphs have been extensively studied in the literature, but they do not appea…