Search results for "Natural Language Processing"

showing 10 items of 413 documents

FrameNet CNL: A Knowledge Representation and Information Extraction Language

2014

The paper presents a FrameNet-based information extraction and knowledge representation framework, called FrameNet-CNL. The framework is used on natural language documents and represents the extracted knowledge in a tailor-made Frame-ontology from which unambiguous FrameNet-CNL paraphrase text can be generated automatically in multiple languages. This approach brings together the fields of information extraction and CNL, because a source text can be considered belonging to FrameNet-CNL, if information extraction parser produces the correct knowledge representation as a result. We describe a state-of-the-art information extraction parser used by a national news agency and speculate that Fram…

Information retrievalParsingKnowledge representation and reasoningbusiness.industryComputer scienceAgency (philosophy)computer.software_genreParaphraseInformation extractionArtificial intelligenceSource textFrameNetbusinesscomputerNatural language processingNatural language
researchProduct

Part-of-speech labeling for Reuters database

2015

Even if the Vector Space Model used for document representation in information retrieval systems integrates a small quantity of knowledge it continues to be used due to its computational cost, speed execution and simplicity. We try to improve this document representation by adding some syntactic information such as the parts of speech. In this paper, we have evaluated three different tagging algorithms in order to select the most suitable tagger for using it to tag the Reuters dataset. In this work, we have evaluated the taggers using only five different parts of speech: noun, verb, adverb, adjective and others. We considered these particular tags being the most representative for describin…

Information retrievalbusiness.industryComputer scienceInformationSystems_INFORMATIONSTORAGEANDRETRIEVALVerbAdverbSpace (commercial competition)Part of speechcomputer.software_genreSequence labelingNounVector space modelArtificial intelligencebusinesscomputerAdjectiveNatural language processing2015 19th International Conference on System Theory, Control and Computing (ICSTCC)
researchProduct

A KST-BASED SYSTEM FOR STUDENT TUTORING

2008

Abstract: A novel assessment procedure based on knowledge space theory (KST) is presented along with a complete implementation of an intelligent tutoring system. (ITS) that has been used to test our theoretical findings. The key idea is that correct assessment of the student knowledge is strictly related to the structure of the domain ontology. Suitable relationships between the concepts must be present to allow the creation of a reverse path from the "knowledge state" representing the student goal to the one that contains her actual knowledge about this topic. Knowledge space theory is a very good framework to guide the process of building the ontology used, by the artificial tutor The sys…

Intelligent systemStructure (mathematical logic)CorrectnessOntologyComputer scienceLatent semantic analysisbusiness.industryOntology (information science)computer.software_genreIntelligent tutoring systemDomain (software engineering)Artificial IntelligenceArtificial intelligenceDialog systemStudentsbusinesscomputerNatural language processing systemKST Student TutoringNatural languageNatural language processingApplied Artificial Intelligence
researchProduct

BUCC Shared Task: Cross-Language Document Similarity

2015

We summarise the organisation and results of the first shared task aimed at detecting the most similar texts in a large multilingual collection. The dataset of the shared was based on Wikipedia dumps with interlanguage links with further filtering to ensure comparability of the paired articles. The eleven system runs we received have been evaluated using the TREC evaluation metrics. 1 Task description Parallel corpora of original texts with their translations provide the basis for multilingual NLP applications since the beginning of the 1990s. Relative scarcity of such resources led to greater attention to comparable (=less parallel) resources to mine information about possible translations…

InterlanguageDocument similarityInformation retrievalComputer sciencebusiness.industryInformationSystems_INFORMATIONSTORAGEANDRETRIEVALArtificial intelligencecomputer.software_genrebusinesscomputerNatural language processingTask (project management)Proceedings of the Eighth Workshop on Building and Using Comparable Corpora
researchProduct

Rigotrio At Semeval-2017 Task 9: Combining Machine Learning And Grammar Engineering For Amr Parsing And Generation

2017

By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua. We strengthen the interlingual aspect of AMR by applying the multilingual Grammatical Framework (GF) for AMR-to-text generation. Our current rule-based GF approach completely covered only 12.3% of the test AMRs, therefore we combined it with state-of-the-art JAMR Generator to see if the combination increases or decreases the overall performance. The combined system achieved the automatic BLEU score of 18.82 and the human Trueskill score of 107.2, to be compared to the plain JAMR Generator results. As for AMR parsing, we added NER extensions to our SemEva…

InterlinguaGenerator (computer programming)Parsingbusiness.industryComputer scienceSpeech recognitionGrammatical Framework02 engineering and technologycomputer.software_genreComputer scienceSemEvallanguage.human_languageTask (project management)020204 information systems0202 electrical engineering electronic engineering information engineeringlanguage020201 artificial intelligence & image processingGrammar engineeringArtificial intelligencebusinesscomputerNatural language processingBLEU
researchProduct

Rough Pragmatic Description Logic

2013

In this chapter, a rough description logic is built on the basis of a pragmatic standpoint of representation of knowledge. The pragmatic standpoint has influenced the acceptance of a broader definition of the semantic network than that appearing in the literature. The definition of the semantic network is a motivation of the introduced semantics of the language of the descriptive logic. First, the theoretical framework of representation of knowledge that was proposed in the papers [24,25] is adjusted to the description of data processing. The pragmatic system of knowledge representation is determined, as well as situations of semantic adequacy and semantic inadequacy for represented knowled…

Interpretation (logic)Knowledge representation and reasoningbusiness.industrycomputer.software_genreSemanticsSemantic networkDescription logicFormal languageInformation systemRough setArtificial intelligencebusinesscomputerNatural language processingMathematics
researchProduct

ETAT: Expository Text Analysis Tool.

2002

Qualitative methods that analyze the coherence of expository texts not only are time consuming, but also present challenges in collecting data on coding reliability. We describe software that analyzes expository texts more rapidly and produces a notable level of objectivity. ETAT (Expository Text Analysis Tool) analyzes the coherence of expository texts. ETAT adopts a symbolic representational system, known as conceptual graph structures. ETAT follows three steps: segmentation of a text into nodes, classification of the unidentified nodes, and linking the nodes with relational arcs. ETAT automatically constructs a graph in the form of nodes and their interrelationships, along with various a…

JavaComputer scienceWritingExperimental and Cognitive Psychologycomputer.software_genreText comprehensionSoftwareMicrocomputersArtificial IntelligenceQuestion answeringSegmentationObjectivity (science)General Psychologycomputer.programming_languageInformation ServicesObserver Variationbusiness.industryReading comprehensionProgramming LanguagesPsychology (miscellaneous)Artificial intelligenceWord ProcessingbusinesscomputerNatural language processingSoftwareCoding (social sciences)Behavior research methods, instruments,computers : a journal of the Psychonomic Society, Inc
researchProduct

Some thoughts about the conceptual / procedural distinction in translation: a key-logging and eye-tracking study of processing effort

2014

This article builds on the conceptual / procedural distinction postulated by Relevance Theory to investigate processing effort in translation task execution. Drawing on relevance-theoretic assumptions, it assumes that instances related to procedural encodings will require more effortful processing not only in relation to the time spent on the task but also in terms of product indicators such as seconds per word and number of micro translation units per word. Drawing on key-logging and eye-tracking data, the article shows that there are statistically significant differences when conceptual and procedural encodings are analysed in selected areas of interest, with instances related to procedur…

Key loggingSeguimiento ocular (eye tracking)Linguistics and LanguageTranslation process research; Relevance Theory; Conceptual; Procedural distinction; Key logging; Eye trackingCodificación conceptual / procedimentalRelation (database)Computer scienceRelevance TheoryRegistros de teclado y ratón (key logging)computer.software_genreKeystroke loggingLanguage and LinguisticsEducationTask (project management)Encoding (semiotics)Teoría de la RelevanciaUNESCO::CIENCIAS DE LAS ARTES Y LAS LETRASEye trackingProceso de traducción; Teoría de la Relevancia; Codificación conceptual / procedimental; Registros de teclado y ratón (key logging); Seguimiento ocular (eye tracking)business.industryRelevance theorySIGNAL (programming language)Traducción e InterpretaciónTranslation process researchProceso de traducción:CIENCIAS DE LAS ARTES Y LAS LETRAS [UNESCO]Eye trackingArtificial intelligenceConceptual / procedural distinctionbusinesscomputerNatural language processingWord (computer architecture)MonTI. Monografías de Traducción e Interpretación
researchProduct

R2D2 at GeoCLEF 2006: A Combined Approach

2007

This paper describes the participation of a combined approach in GeoCLEF-2006. We have participated in Monolingual English Task and we present joint work of the three groups or teams belonging to the project R2D2 with a new system, combining the three individual systems of these teams. We consider that research in the area of GIR is still in its very early stages, therefore, although a voting system could improve the individual results of each system, we have to further investigate different ways to achieve a better combination of these systems.

Knowledge managementGeographic information systembusiness.industryComputer sciencemedia_common.quotation_subjectcomputer.software_genreCombined approachTask (project management)Query expansionVotingArtificial intelligencebusinesscomputerNatural language processingmedia_common
researchProduct

Handling Context-Sensitive Temporal Knowledge from Multiple Differently Ranked Sources

1999

In this paper we develop one way to represent and reason with temporal relations in the context of multiple experts. Every relation between temporal intervals consists of four endpoints’ relations. It is supposed that the context we know is the value of every expert competence concerning every endpoint relation. Thus the context for an interval temporal relation is one kind of compound expert’s rank, which has four components appropriate to every interval endpoints’ relation. Context is being updated after every new opinion is being added to the previous opinions about certain temporal relation. The context of a temporal relation collects all support given by different experts to all compon…

Knowledge representation and reasoningComputer sciencebusiness.industryProbability distributionData miningArtificial intelligencecomputer.software_genrebusinessKnowledge acquisitioncomputerWeighted arithmetic meanNatural language processing
researchProduct