Search results for "Natural Language Processing"
showing 10 items of 413 documents
Dynamic assessment of word derivational knowledge: Tracing the development of a learner
2016
The present paper reports on a case study that explored the applicability of dynamic assessment (DA) for promoting learners’ word derivational knowledge in English as a second or a foreign language (L2). One learner’s performance on tasks assessing his word derivational knowledge was measured four times. The first two measurements were conducted before and after three weekly human-mediated DA sessions and the last two, which took place a year and a half later, before and after three weekly computerised DA sessions. Think aloud protocols and interviews were used to trace changes in the learner’s use of strategies and knowledge sources. The results revealed that following the dynamic assessme…
Cognitive Linguistics as the Underlying Framework for Semantic Annotation
2012
In recent years many attempts have been made to design suitable sets of rules aimed at extracting the semantic meaning from plain text, and to achieve annotation, but very few approaches make extensive use of grammars. Current systems are mainly focused on extracting the semantic role of the entities described in the text. This approach has limitations: in such applications the semantic role is conceived merely as the meaning of the involved entities without considering their context. As an example, current semantic annotators often specify a date entity without any annotation regarding the kind of the date itself i.e. a birth date, a book publication date, and so on. Moreover, these system…
Cognitive Computing supported Medical Decision Support System for Patient’s Driving Assessment
2018
To smartly utilize a huge and constantly growing volume of data, improve productivity and increase competitiveness in various fields of life; human requires decision making support systems that efficiently process and analyze the data, and, as a result, significantly speed up the process. Similarly to all other areas of human life, healthcare domain also is lacking Artificial Intelligence (AI) based solution. A number of supervised and unsupervised Machine Learning and Data Mining techniques exist to help us to deal with structured data. However, in a real life, we pretty much deal with unstructured data that hides useful knowledge and valuable information inside human-readable plain texts,…
Towards Equivalence Links between Senses in PlWordNet and Princeton WordNet
2017
AbstractThe paper focuses on the issue of creating equivalence links in the domain of bilingual computational lexicography. The existing interlingual links between plWordNet and Princeton WordNet synsets (sets of synonymous lexical units – lemma and sense pairs) are re-analysed from the perspective of equivalence types as defined in traditional lexicography and translation. Special attention is paid to cognitive and translational equivalents. A proposal of mapping lexical units is presented. Three types of links are defined: super-strong equivalence, strong equivalence and weak implied equivalence. The strong equivalences have a common set of formal, semantic and usage features, with some o…
Evaluation and Self-Evaluation in Simultaneous Translation: Assessments Methods
2012
Abstract The nature of evaluation and self-evaluation in simultaneous interpretation is based on the close connection between the main text (the version proposed by the speaker) and the interpreter's version. Between these two elements a number of variables emerge, that can damage the efficiency and the accuracy of simultaneous interpretation. The intention of our study is to propose a set of scientific methods and tools in order to offer to the interpreter the possibility of a self-assessment and the benefit of an appropriate evaluation of his work. In order to achieve these goals we used several methods, including experiments, case studies, questionnaires, evaluation scales. Research subj…
Smart and valued? ICT urban (transport) solutions in the city official communication
2022
To optimize the everyday functioning of a city, urban authorities can implement smart city tools and solutions. Mobility is a typical field associated with the concept of a smart city. It is interesting to take a closer look at the solutions applied through the information accessible on the official websites, while exploring, at the same time, the possibilities offered by new research tools. The main objective of this work is to establish the significance of the information and communication technologies (ICT) in the process of creating smart mobility in a smart city, based on the texts posted on official websites. Using the natural language processing (NLP) methods and tools offered by the…
Efecto de las Características del Problema, Captación de su Estructura y Uso de Analogías sobre el Éxito de los Estudiantes de Secundaria en la Resol…
2015
This study analyses the influence of academic level, academic itinerary, word problem’s context and structure, capturing problem structure, and using analogies on problem-solving. A factorial design was used with one within-subjects variable and several between-subjects variables, which have been selected depending on the hypothesis in question. Two types of booklets containing two word problems and questions about capturing problem structure and using analogies in problem solving, were administered to a total of 181 grade-10 and grade-12 students. The results of non-parametric statistical tests showed that: a) Academic level and academic itinerary are decisive variables in problem solving,…
Inter-annotator agreement in spoken language annotation: Applying uα-family coefficients to discourse segmentation
2021
As databases make Corpus Linguistics a common tool for most linguists, corpus annotation becomes an increasingly important process. Corpus users do not need only raw data, but also annotated data, submitted to tagging or parsing processes through annotation protocols. One problem with corpus annotation lies in its reliability, that is, in the probability that its results can be replicable by independent researchers. Inter-annotation agreement (IAA) is the process which evaluates the probability that, applying the same protocol, different annotators reach similar results. To measure agreement, different statistical metrics are used. This study applies IAA for the first time to the Valencia E…
Measuring syntactic complexity in learner Finnish
2020
In the study of complexity, accuracy and fluency (CAF), syntactic complexity can be measured by a multitude of measures. Traditionally, the measures are quantitative and they use production units such as words, clauses, T -units, and sentences. Despite the vast number o f measures available, many studies have used only one or two of them, or parallel ones tapping the same component of complexity. The present study explores syntactic complexity using seven frequently used quantitative complexity measures to gauge different facets of complexity in written learner Finnish. The data of the study consist of texts written by adult and adolescent language learners, and they cover proficiency level…
Words, clauses, sentences, and T-units in learner language: Precise and objective units of measure?
2020
In research on learner language complexity, accuracy and fluency (CAF), syntactic complexity is often studied with quantitative measures based on words, clauses, sentences, and T-units. The findings have been mixed, but segmenting learner language into these units of measure has seldom been problematised, even if the need for accurate coding is well known. The present study explores words, clauses, sentences, and T-units as production units in written learner language using a corpus of 352 L2 Finnish texts (28,813 words). The results illustrate how written learner language can be hard to fit into the production unit categories, which are essential for the most frequently used quantitative m…