The paper describes the FidaPLUS corpus which is an upgrade of the Slovenian reference corpus. The corpus has been improved on various levels: size, up-todateness, quality of linguistic annotation (lemmatization, POS-tagging), availability and user-friendliness of the on-line concordancer. It has also been implemented in the Sketch Engine software which produces one-page automatic, corpus-based...

This tutorial presents a corpus-driven, pattern-based empirical approach to meaning representation and computation. Patterns in text are everywhere, but techniques for identifying and processing them are still rudimentary. Patterns are not merely syntactic but syntagmatic: each pattern identifies a lexico-semantic clause structure consisting of a predicator (verb or predicative adjective) toget...

Multiword expressions as they appear as nominal compounds, collocational forms, and idioms are now leveraged in educational technology in assessment and instruction contexts. The talk will focus on how multiword expression identification is used in different kinds of educational applications, including automated essay evaluation, and teacher professional development in curriculum development fo...

Metaphor is a pervasive phenomenon in natural language. This paper focuses on metaphor identification. Based on the linguistic definition, an improved classification system of Chinese metaphors is presented, classifying metaphorical language into two categories: referential metaphor with ten subclasses and collocational metaphor with five subclasses. Furthermore, a novel pattern matching algori...

The goal of this paper is to use a largescale corpus, i.e. the Gigaword Corpus via the interface of Chinese Sketch Engine, to determine underlying reasons between source and target domain pairings for conceptual metaphors, called Mapping Principles. In particular, we will employ a frequency-based collocational approach to examine metaphors that use the source domain of BUILDING in Mandarin Chin...

Collocational word similarity is considered a source of text cohesion that is hard to measure and quantify. The work presented here explores the use of information from a training corpus in measuring word similarity and evaluates the method in the text segmentation task. An implementation, the VecTile system, produces similarity curves over texts using pre-compiled vector representations of the...

The paper presents a corpus-based study aimed at an analysis of ontological and terminological commitments in the discourse of specialist communities. The analyzed corpus contains the lectures delivered by the Nobel Prize winners in Physics and Economics. The analysis focuses on (a) the collocational use of automatically identified domain-specific terms and (b) a description of metadiscourse in...

This paper presents a method for extracting multi-word collocations (MWCs) from text corpora, which is based on the previous extraction of syntactically bound collocation bigrams. We describe an iterative word linking procedure which relies on a syntactic criterion and aims at building up arbitrarily long expressions that represent multi-word collocation candidates. We propose several measures ...