Search results for "Natural language"

showing 10 items of 650 documents

Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability

2020

Despite significant effort, building models that are both interpretable and accurate is an unresolved challenge for many pattern recognition problems. In general, rule-based and linear models lack accuracy, while deep learning interpretability is based on rough approximations of the underlying inference. Using a linear combination of conjunctive clauses in propositional logic, Tsetlin Machines (TMs) have shown competitive performance on diverse benchmarks. However, to do so, many clauses are needed, which impacts interpretability. Here, we address the accuracy-interpretability challenge in machine learning by equipping the TM clauses with integer weights. The resulting Integer Weighted TM (…

FOS: Computer and information sciencesBoosting (machine learning)Theoretical computer scienceinteger-weighted Tsetlin machineGeneral Computer ScienceComputer scienceComputer Science - Artificial Intelligence0206 medical engineeringNatural language understandingInference02 engineering and technologycomputer.software_genre0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceTsetlin machineVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550InterpretabilityArtificial neural networkLearning automatabusiness.industryDeep learningGeneral Engineeringinterpretable machine learningrule-based learninginterpretable AIPropositional calculusSupport vector machineArtificial Intelligence (cs.AI)TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESXAIPattern recognition (psychology)020201 artificial intelligence & image processinglcsh:Electrical engineering. Electronics. Nuclear engineeringArtificial intelligencebusinesslcsh:TK1-9971computer020602 bioinformaticsInteger (computer science)
researchProduct

Polysemy in Controlled Natural Language Texts

2015

Computational semantics and logic-based controlled natural languages (CNL) do not address systematically the word sense disambiguation problem of content words, i.e., they tend to interpret only some functional words that are crucial for construction of discourse representation structures. We show that micro-ontologies and multi-word units allow integration of the rich and polysemous multi-domain background knowledge into CNL thus providing interpretation for the content words. The proposed approach is demonstrated by extending the Attempto Controlled English (ACE) with polysemous and procedural constructs resulting in a more natural CNL named PAO covering narrative multi-domain texts.

FOS: Computer and information sciencesComputer Science - Computation and LanguageInterpretation (logic)Computer sciencebusiness.industryRepresentation (arts)Content wordcomputer.software_genrelanguage.human_languageControlled natural languageComputational semanticslanguageAttempto Controlled EnglishArtificial intelligencePolysemybusinessComputation and Language (cs.CL)computerNatural languageNatural language processing
researchProduct

Towards the evaluation of automatic simultaneous speech translation from a communicative perspective

2021

In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine…

FOS: Computer and information sciencesComputer Science - Computation and LanguageMachine translationEnd userComputer sciencebusiness.industrymedia_common.quotation_subjectSample (statistics)Context (language use)Intelligibility (communication)computer.software_genreSpeech translationQuality (business)Artificial intelligencebusinessComputation and Language (cs.CL)computerInterpreterNatural language processingmedia_commonProceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
researchProduct

Structured query construction via knowledge graph embedding

2020

In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer Science - Computation and LanguageComputer Science - Artificial Intelligenceknowledge graph embeddingnatural language question answeringkyselykieletMachine Learning (cs.LG)luonnollinen kieliArtificial Intelligence (cs.AI)knowledge graphquery constructionComputation and Language (cs.CL)tietomallit
researchProduct

Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications

2019

Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled tex…

FOS: Computer and information sciencesComputer Science - Machine LearningGeneral Computer ScienceComputer sciencetext categorizationNatural language understandingDecision treeMachine Learning (stat.ML)02 engineering and technologyVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550::Annen informasjonsteknologi: 559Machine learningcomputer.software_genresupervised learningMachine Learning (cs.LG)Naive Bayes classifierText miningStatistics - Machine Learning0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceTsetlin machinehealth informaticsInterpretabilityPropositional variableClassification algorithmsArtificial neural networkbusiness.industryDeep learning020208 electrical & electronic engineeringGeneral EngineeringRandom forestSupport vector machinemachine learningCategorization020201 artificial intelligence & image processingArtificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringbusinessPrecision and recallcomputerlcsh:TK1-9971
researchProduct

Cyclic Complexity of Words

2014

We introduce and study a complexity function on words $c_x(n),$ called \emph{cyclic complexity}, which counts the number of conjugacy classes of factors of length $n$ of an infinite word $x.$ We extend the well-known Morse-Hedlund theorem to the setting of cyclic complexity by showing that a word is ultimately periodic if and only if it has bounded cyclic complexity. Unlike most complexity functions, cyclic complexity distinguishes between Sturmian words of different slopes. We prove that if $x$ is a Sturmian word and $y$ is a word having the same cyclic complexity of $x,$ then up to renaming letters, $x$ and $y$ have the same set of factors. In particular, $y$ is also Sturmian of slope equ…

FOS: Computer and information sciencesDiscrete Mathematics (cs.DM)Formal Languages and Automata Theory (cs.FL)Computer Science - Formal Languages and Automata Theory0102 computer and information sciences68R15Characterization (mathematics)[INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM]01 natural sciencesTheoretical Computer ScienceCombinatoricsConjugacy class[INFO.INFO-FL]Computer Science [cs]/Formal Languages and Automata Theory [cs.FL][MATH.MATH-CO]Mathematics [math]/Combinatorics [math.CO]FOS: MathematicsDiscrete Mathematics and CombinatoricsMathematics - Combinatorics0101 mathematics[MATH]Mathematics [math]Discrete Mathematics and CombinatoricMathematicsDiscrete mathematicsFactor complexity010102 general mathematicsSturmian wordSturmian wordComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Sturmian wordsCyclic complexity factor complexity Sturmian words minimal forbidden factorInfimum and supremumToeplitz matrixComputational Theory and Mathematics010201 computation theory & mathematicsCyclic complexityBounded functionComplexity functionCombinatorics (math.CO)Word (group theory)Computer Science::Formal Languages and Automata TheoryComputer Science - Discrete Mathematics
researchProduct

Quantum, stochastic, and pseudo stochastic languages with few states

2014

Stochastic languages are the languages recognized by probabilistic finite automata (PFAs) with cutpoint over the field of real numbers. More general computational models over the same field such as generalized finite automata (GFAs) and quantum finite automata (QFAs) define the same class. In 1963, Rabin proved the set of stochastic languages to be uncountable presenting a single 2-state PFA over the binary alphabet recognizing uncountably many languages depending on the cutpoint. In this paper, we show the same result for unary stochastic languages. Namely, we exhibit a 2-state unary GFA, a 2-state unary QFA, and a family of 3-state unary PFAs recognizing uncountably many languages; all th…

FOS: Computer and information sciencesFINITE AUTOMATAClass (set theory)Unary operationFormal Languages and Automata Theory (cs.FL)QUANTUM FINITE AUTOMATACOMPUTATIONAL MODELBINARY ALPHABETSFOS: Physical sciencesComputer Science - Formal Languages and Automata TheoryComputer Science::Computational ComplexityPROBABILISTIC FINITE AUTOMATAREAL NUMBERUNARY LANGUAGESQuantum finite automataCUT-POINTMathematicsReal numberDiscrete mathematicsQuantum PhysicsFinite-state machineGENERALIZED FINITE AUTOMATAComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)STOCHASTIC SYSTEMSAutomatonSTOCHASTIC LANGUAGESMathematics::LogicProbabilistic automatonComputer Science::Programming LanguagesQUANTUM THEORYUncountable setQuantum Physics (quant-ph)Computer Science::Formal Languages and Automata TheoryGENERALIZED FINITE AUTOMATON
researchProduct

On generalized Lyndon words

2018

Abstract A generalized lexicographical order on infinite words is defined by choosing for each position a total order on the alphabet. This allows to define generalized Lyndon words. Every word in the free monoid can be factorized in a unique way as a nonincreasing factorization of generalized Lyndon words. We give new characterizations of the first and the last factor in this factorization as well as new characterization of generalized Lyndon words. We also give more specific results on two special cases: the classical one and the one arising from the alternating lexicographical order.

FOS: Computer and information sciencesGeneral Computer ScienceDiscrete Mathematics (cs.DM)Computer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)68R15Characterization (mathematics)Lexicographical orderTheoretical Computer ScienceLyndon wordsCombinatoricsFactorizationPosition (vector)Free monoidFOS: MathematicsOrder (group theory)Mathematics - CombinatoricsCombinatorics (math.CO)Word (group theory)Computer Science::Formal Languages and Automata TheoryMathematicsComputer Science - Discrete Mathematics
researchProduct

On the Lie complexity of Sturmian words

2022

Bell and Shallit recently introduced the Lie complexity of an infinite word $s$ as the function counting for each length the number of conjugacy classes of words whose elements are all factors of $s$. They proved, using algebraic techniques, that the Lie complexity is bounded above by the first difference of the factor complexity plus one; hence, it is uniformly bounded for words with linear factor complexity, and, in particular, it is at most 2 for Sturmian words, which are precisely the words with factor complexity $n+1$ for every $n$. In this note, we provide an elementary combinatorial proof of the result of Bell and Shallit and give an exact formula for the Lie complexity of any Sturmi…

FOS: Computer and information sciencesGeneral Computer ScienceSettore INF/01 - InformaticaDiscrete Mathematics (cs.DM)Formal Languages and Automata Theory (cs.FL)Sturmian wordComputer Science - Formal Languages and Automata TheoryComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)G.2.168R15Lie complexityTheoretical Computer ScienceLie complexity Sturmian wordFOS: MathematicsMathematics - CombinatoricsCombinatorics (math.CO)Computer Science::Formal Languages and Automata TheoryComputer Science - Discrete Mathematics
researchProduct

On the Structure of Bispecial Sturmian Words

2013

A balanced word is one in which any two factors of the same length contain the same number of each letter of the alphabet up to one. Finite binary balanced words are called Sturmian words. A Sturmian word is bispecial if it can be extended to the left and to the right with both letters remaining a Sturmian word. There is a deep relation between bispecial Sturmian words and Christoffel words, that are the digital approximations of Euclidean segments in the plane. In 1997, J. Berstel and A. de Luca proved that \emph{palindromic} bispecial Sturmian words are precisely the maximal internal factors of \emph{primitive} Christoffel words. We extend this result by showing that bispecial Sturmian wo…

FOS: Computer and information sciencesGeneral Computer ScienceSpecial factorDiscrete Mathematics (cs.DM)Computer Networks and CommunicationsApproximations of πFormal Languages and Automata Theory (cs.FL)Computer Science - Formal Languages and Automata TheoryEnumerative formula68R15Characterization (mathematics)Minimal forbidden wordTheoretical Computer ScienceCombinatoricsComputer Science::Discrete MathematicsEuclidean geometryPhysics::Atomic PhysicsMathematicsChristoffel symbolsApplied MathematicsPalindromeSturmian wordSturmian wordComputer Science::Computation and Language (Computational Linguistics and Natural Language and Speech Processing)Combinatorics on wordsComputational Theory and MathematicsWord (group theory)Computer Science::Formal Languages and Automata TheoryChristoffel wordComputer Science - Discrete Mathematics
researchProduct