This paper presents a linguistic approach based on weighted-finite state transducers for the lexical normalisation of Spanish Twitter messages. The system developed consists of transducers that are applied to out-of-vocabulary tokens. Transducers implement linguistic models of variation that generate sets of candidates according to a lexicon. A statistical language model is used to obtain the m...

Introduction The fundamental task of ontology matching is based on measuring the similarity between two ontology concepts [1]. However, we argue that a deeper semantic, terminological and linguistic analysis of specialized domain vocabularies is needed in order to establish a more sophisticated similarity measure that caters for the specific characteristics of this data. In particular we propos...

The orthographical complexity of Chinese, Japanese and Korean (CJK) poses a special challenge to the developers of computational linguistic tools, especially in the area of intelligent information retrieval. These difficulties are exacerbated by the lack of a standardized orthography in these languages, especially the highly irregular Japanese orthography. This paper focuses on the typology of ...

Human languages contain very little unconditioned variation. In contexts where language learners are exposed to input that contains inconsistencies, they tend to regularise it, either by eliminating competing variants, or conditioning variant use on the context. In the present study we compare regularisation behaviour across linguistic levels, looking at how adult learners respond to variabilit...

In this work, we extend the genetic lateral tuning of membership functions [1] based on the linguistic 2-tuples representation [2], in order to also perform a tuning of the support amplitude of the membership functions. To do so, we present a new symbolic representation which extends the linguistic 2-tuples representation model with a parameter β to represent the amplitude variation of the supp...

Research articles are acknowledged to be the most important form of scientific discourse. Abstracts are, apart from the title, the first meeting of readers with research articles. Independently of their traditional purpose to summarize research articles, abstracts have become crucial for readers in the decision process of reading the text further, especially nowadays due to the vast amount of s...

It has been widely observed in the literature that not only learner varieties but also contact varieties differ in their prosody from the standard variety. The article aims at providing a unified account to the linguistic variation in prosodic focus marking found across learner and contact varieties of the same language, South African English. The notion of markedness allows singling out prosod...

Although it prefigures many advances in linguistic theory, the scholarship of nineteenth century scholar Mikołaj Kruszewski is today largely forgotten. In these papers I hope to partially rectify this situation by introducing Kruszewski’s insights to modern discourse on phonology. In addition to a detailed summary of Kruszewski’s major work, An Outline of the Science of Language (Očerk Nauki O ...

A potentially fruitful area for applied linguistic research is the nature of the linguistic systems used by second language learners as they learn--or even after they appear to have stopped learning. It has been suggested at various times that the findings of this sort of research would be useful not only to language teachers and textbook writers, but also to our understanding of language conta...