George K. Mikros

Word Length, Word Frequencies and Zipf’s Law in the Greek Language

The aim of this paper is to report for the first time the 1000 most common words and lemmas of Modern Greek and some of their quantitative characteristics. The frequency word list produced is based on the Hellenic National Corpus (HNC), a corpus of Modern Greek language consisting of about 13 million words of written texts. In particular, we investigate the application of Zipf’s law in both the 1000 most common words and lemmas. In addition we examine the frequency distribution of the grammatical categories in the 1000 most common words and lemmas as well as the average word length in the whole HNC and the growth of the average word length as a function of the number of the most common words.

Basic Quantitative Characteristics of the Modern Greek Language Using the Hellenic National Corpus

Modern Greek is one of the least quantitatively studied modern European languages and the goal of this paper is to fill this relative void. We use the Hellenic National Corpus (HNC), which is a growing corpus that currently includes 33 million words. The corpus and all the tools used in our work were developed by the Institute for Language and Speech Processing (ILSP). In this paper we focus on three main areas: the lists of the 1000 most common words and lemmas, word length and letter frequency. We also make some comparisons with earlier work, in which we had used the previous 13 million word edition of the HNC.

Sentiment Analysis of Hotel Reviews in Greek: A Comparison of Unigram Features

Web 2.0 has become a very useful information resource nowadays, as people are strongly inclined to express online their opinion in social media, blogs and review sites. Sentiment analysis aims at classifying documents as positive or negative according to their overall expressed sentiment. In this paper, we create a sentiment classifier applying Support Vector Machines on hotel reviews written in Modern Greek. Using a unigram language model, we compare two different methodologies and the emerging results look very promising.

What's in a dialogic construction? A constructional approach to polysemy and the grammar of challenge

Abstract In this paper we address lexical polysemy in a constructional perspective, arguing that each of the conversational meanings we identify for Modern Greek ela (2nd person singular imperative of the verb erxome ‘come’) is appropriately modeled as a conceptual gestalt of formal (including prosodic) and semantic-pragmatic properties. In turn-initial position, ela is used to challenge a preceding utterance; we show that the variations in the kind of challenge expressed are systematically tied to the word that follows ela, the speech act force and the sentence type of the preceding utterance, and finally prosodic and textual cues. To the extent that these varieties of conversational challenge are conditioned by particular contextual features, we treat them as a family of related constructions whose common features can be captured in the form of a generalized ela construction abstracted from the different sub-patterns. Our analysis thus demonstrates the appropriateness of a constructional framework for dealing with the different kinds of parameters involved in dialogic meaning and strongly suggests that at least some of the variation inherent in discourse is amenable to a grammatical description, so that sentence-level and supra-clause patterns can be analyzed in a uniform way.

Correlations and Potential Cross-Linguistic Indicators of Writing Style

Abstract In this paper, we present preliminary results on how an individual’s writing style persists even across languages. In other words, what aspects of an individual’s writing will persist irrespective of the language in which he or she writes? We argue that cognitive and social traits are likely to persist and demonstrate this by two separate analyses of bilingual corpora using the same individuals. We show that for various measures of linguistic complexity (which we consider to be a cognitive variable) and participation in specific social conventions (a social one), the correlation between scores on the two languages studied is significantly higher than would be expected by chance. We argue that this type of correlation may permit cross-linguistic authorship attribution.

Developing a Scoring Algorithm for Automatic Pronunciation Assessment of Modern Greek

Abstract In recent years, renewed focus has fallen on pronunciation; the development of pronunciation skills is now considered an important component of communicative competence. Pronunciation assessment and the provision of pertinent feedback have become more or less standard features within Computer-Assisted Language Learning (CALL). In this paper we will present the features and technologies deployed for the acquisition of Greek phonetics in a courseware for English-speaking adult learners of Greek; in the light of certain limitations of this courseware regarding pronunciation assessment, we will describe a scoring algorithm for automatic pronunciation assessment of Modern Greek which may address these shortcomings.