Search results for "natural language processing"
showing 10 items of 413 documents
First results of PACTE group's experimental research on translation competence acquisition : the acquisition of declarative knowledge of translation
2014
Autors llistats per ordre alfabètic. Investigadora principal: A. Hurtado Albir This paper presents the first results of empirical-experimental research into the Acquisition of Translation Competence (ATC): the acquisition of declarative knowledge about translation. This study is based on our previous research about Translation Competence (TC). Some of the data collection instruments have, however, been adapted for current use. Details of our research design include type of study, universe and sample population, study variables, data collection instruments, and data analysis processes. The dependent variables were knowledge of translation; translation project; identification and solution of …
Non-cognate translation priming effects in the same–different task: evidence for the impact of “higher level” information
2015
Norris and colleagues have proposed that priming effects observed in the masked prime same–different task are based solely on pre-lexical orthographic information. This proposal was evaluated by examining translation priming effects from non-cognate translation equivalents using both Spanish–English and Japanese–English bilinguals in the same–different task. Although no priming was observed for Spanish–English bilinguals, who also produced very little translation priming in a lexical decision task, significant priming was observed for Japanese–English bilinguals. These results indicate that, although most of the priming in the same–different task has an orthographic basis, other types of pr…
A probabilistic approach to learning a visually grounded language model through human-robot interaction
2010
A Language is among the most fascinating and complex cognitive activities that develops rapidly since the early months of infants' life. The aim of the present work is to provide a humanoid robot with cognitive, perceptual and motor skills fundamental for the acquisition of a rudimentary form of language. We present a novel probabilistic model, inspired by the findings in cognitive sciences, able to associate spoken words with their perceptually grounded meanings. The main focus is set on acquiring the meaning of various perceptual categories (e. g. red, blue, circle, above, etc.), rather than specific world entities (e. g. an apple, a toy, etc.). Our probabilistic model is based on a varia…
Semi-automatic Quasi-morphological Word Segmentation for Neural Machine Translation
2018
This paper proposes the Prefix-Root-Postfix-Encoding (PRPE) algorithm, which performs close-to-morphological segmentation of words as part of text pre-processing in machine translation. PRPE is a cross-language algorithm requiring only minor tweaking to adapt it for any particular language, a property which makes it potentially useful for morphologically rich languages with no morphological analysers available. As a key part of the proposed algorithm we introduce the ‘Root alignment’ principle to extract potential sub-words from a corpus, as well as a special technique for constructing words from potential sub-words. We conducted experiments with two different neural machine translation sys…
What to Expect and What to Focus on in SQL Query Teaching
2019
In the process of learning a new computer language, writing erroneous statements is part of the learning experience. However, some errors persist throughout the query writing process and are never corrected. Structured Query Language (SQL) consists of a number of different concepts such as expressions, joins, grouping and ordering, all of which by nature invite different possible errors in the query writing process. Furthermore, some of these errors are relatively easy for a student to fix when compared to others. Using a data set from three student cohorts with the total of 744 students, we set out to explore which types of errors are persistent, i.e., more likely to be left uncorrected by…
A Neural Network model for the Evaluation of Text Complexity in Italian Language: a Representation Point of View
2018
Abstract The goal of a text simplification system (TS) is to create a new text suited to the characteristics of a reader, with the final goal of making it more understandable.The building of an Automatic Text Simplification System (ATS) cannot be separated from a correct evaluation of the text complexity. In fact the ATS must be capable of understanding if a text should be simplified for the target reader or not. In a previous work we have presented a model capable of classifying Italian sentences based on their complexity level. Our model is a Long Short Term Memory (LSTM) Neural Network capable of learning the features of easy-to-read and complex-to-read sentences autonomously from a anno…
Formative feedback to transfer self-regulation of task-oriented reading strategies
2016
The study includes two experiments to analyse the effects of automatic formative feedback designed to promote the transfer of self-regulation of strategic decisions in task-oriented reading e.g. answering questions from an available text. Secondary-school students read and answered multiple-choice comprehension questions from two texts having them available while receiving consistent feedback about their performance and strategic decisions. Then, they read a different text and answered questions also with the text available, but receiving no feedback. In Experiment 1, we tested two feedback procedures that differed in task conditions and the feedback information associated to these conditio…
Visualization of tonal content with self-organizing maps and self-similarity matrices
2005
This article presents a dynamic model of tonality perception based on a short-term memory model and a self-organizing map (SOM). The model can be used for dynamic visualization of perceived tonal content, making it possible to examine the clarity and locus of tonality at any given point of time. This article also presents a method for the visualization of tonal structure using self-similarity matrices. The methods are applied to compositions of J. S. Bach, S. Barber, and J. Pachelbel. Finally, a real-time application embracing the tonality perception model is presented.
A Layered Architecture for Sentiment Classification of Products Reviews in Italian Language
2017
The paper illustrates a system for the automatic classification of the sentiment orientation expressed into reviews written in Italian language. A proper stratification of linguistic resources is adopted in order to solve the lacking of an opinion lexicon specifically suited for the Italian language. Experiments show that the proposed system can be applied to a wide range of domains.
Positionless aspect based sentiment analysis using attention mechanism.
2021
Abstract Aspect-based sentiment analysis (ABSA) aims at identifying fine-grained polarity of opinion associated with a given aspect word. Several existing articles demonstrated promising ABSA accuracy using positional embedding to show the relationship between an aspect word and its context. In most cases, the positional embedding depends on the distance between the aspect word and the remaining words in the context, known as the position index sequence. However, these techniques usually employ both complex preprocessing approaches with additional trainable positional embedding and complex architectures to obtain the state-of-the-art performance. In this paper, we simplify preprocessing by …