Search results for "natural language"
showing 10 items of 650 documents
Mining Interpretable Rules for Sentiment and Semantic Relation Analysis Using Tsetlin Machines
2020
Tsetlin Machines (TMs) are an interpretable pattern recognition approach that captures patterns with high discriminative power from data. Patterns are represented as conjunctive clauses in propositional logic, produced using bandit-learning in the form of Tsetlin Automata. In this work, we propose a TM-based approach to two common Natural Language Processing (NLP) tasks, viz. Sentiment Analysis and Semantic Relation Categorization. By performing frequent itemset mining on the patterns produced, we show that they follow existing expert-verified rule-sets or lexicons. Further, our comparison with other widely used machine learning techniques indicates that the TM approach helps maintain inter…
A Sub-Symbolic Approach to Word Modelling for Domain Specific Speech Recognition
2006
In this work a sub-symbolic technique for automatic, data driven language models construction is presented. Such a technique can be used to arrange a language-modelling module, which can be easily integrated in existing speech recognition architectures, such as the well-found HTK architecture. The proposed technique takes advantages from both the traditional LSA approach and from a novel application of a probability space metric known as "Hellinger's distance". Experimental trials are also presented, in order to validate the proposed approach.
Application of the Error Correcting Grammatical Inference Method (ECGI) to Multi-Speaker Isolated Word Recognition
1988
It is well known that speech signals constitute highly structured objects which are composed of different kinds of subobjects such as words, phonemes, etc. This fact has motivated several researchers to propose different models which more or less explicitly assume the structural nature of speech. Notable examples of these models are Markov models /Bak 75/, /Jel 76/; the famous Harpy /Low 76/; Scriber and Lafs /Kla 80/; and many others works in which the convenience of some structural model of the speech objects considered is explicitly claimed /Gup 82/, /Lev 83/, /Cra 84/, /Sca 85/, /Kam 85/, /Sau 85/, /Rab 85/, /Kop 85/, /Sch 85/, /Der 86/, /Tan 86/.
A practical solution to the problem of automatic word sense induction
2004
Recent studies in word sense induction are based on clustering global co-occurrence vectors, i.e. vectors that reflect the overall behavior of a word in a corpus. If a word is semantically ambiguous, this means that these vectors are mixtures of all its senses. Inducing a word's senses therefore involves the difficult problem of recovering the sense vectors from the mixtures. In this paper we argue that the demixing problem can be avoided since the contextual behavior of the senses is directly observable in the form of the local contexts of a word. From human disambiguation performance we know that the context of a word is usually sufficient to determine its sense. Based on this observation…
Automatic identification of word translations from unrelated English and German corpora
1999
Algorithms for the alignment of words in translated texts are well established. However, only recently new approaches have been proposed to identify word translations from non-parallel or even unrelated texts. This task is more difficult, because most statistical clues useful in the processing of parallel texts cannot be applied to non-parallel texts. Whereas for parallel texts in some studies up to 99% of the word alignments have been shown to be correct, the accuracy for non-parallel texts has been around 30% up to now. The current study, which is based on the assumption that there is a correlation between the patterns of word co-occurrences in corpora of different languages, makes a sign…
Read&Answer, A Tool to Capture on-Line Processing of Electronic Texts
2009
This paper is aimed at presenting Read&Answer, a tool that records reading times, one of the main on-line methods employed in text processing research. Read&Answer allows the recording, analysis and interpretation of the learner processing in order to test specific hypotheses and explain final comprehension results. First, we will describe the tool, and then we will briefly explain some research studies using the tool. We will show how Read&Answer can be used in combination with another on-line method extensively employed in text processing research, i.e., verbal protocols, and we will also compare Read&Answer with eye movement tracking, a widely accepted on-line reading times technique.
Grammar is the heart of language : grammar and its role in language learning among Finnish university students
2015
This article presents and discusses views on grammar and its role in formal language learning amongst Finnish university students. The results are based on a questionnaire which was distributed to students at the University of Jyväskylä as part of institutional action research. The background to the project was a feeling amongst some teachers of increased divergence between student respectively language teacher understandings of the role of grammar in language teaching. This concern raised the need to find out how students view grammar. The knowledge about thoughts on grammar amongst students would then help teachers to adjust and adept the way grammar is used in language teaching. The main…
Knowledge-based verification of concatenative programming patterns inspired by natural language for resource-constrained embedded devices
2020
We propose a methodology to verify applications developed following programming patterns inspired by natural language that interact with physical environments and run on resource-constrained interconnected devices. Natural language patterns allow for the reduction of intermediate abstraction layers to map physical domain concepts into executable code avoiding the recourse to ontologies, which would need to be shared, kept up to date, and synchronized across a set of devices. Moreover, the computational paradigm we use for effective distributed execution of symbolic code on resource-constrained devices encourages the adoption of such patterns. The methodology is supported by a rule-based sys…
Language Learning Methodology for Adults: A Study of Linguistic Transfer
2014
Abstract The purpose of the present research is to bring together the evidence on transfer in adult L2 and L3 language acquisition and investigate the use and the relationship between languages in contact. The role of linguistic transfer ( Odlin, 1989 ) i.e. the imposition of previously learned patterns onto a new learning situation, has a facilitation or inhibition effect on the learner's progress in mastering a new language (L2 or L3). Our findings reveal that the cross-linguistic influence occurs both from the direction of the L2 to the L3 and from the L3 to the L2 ( Odlin, 2003 , Jarvis and Pavlenko, 2008 ). In the case of our participants, in the acquisition of L2 as the foreign langua…
Implicit learning
2008
International audience; All of us have learned much about language, music, physical or social environment, and other complex domains, out of any intentional attempts to acquire information. This chapter describes first how studies investigating this form of learning in laboratory situations have shifted from a rule-based interpretation to interpretations assuming a progressive tuning to the statistical regularities of the environment. The next section examines the potential of statistical learning, and whether statistical learning stems from statistical computations or chunk formation. Then the acceptations in which this form of learning may be qualified as implicit are analysed. Finally, i…