Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for...

Lexical substitution is a task of determining a meaning-preserving replacement for a word in context. We report on a preliminary study of this task for the Croatian language on a small-scale lexical sample dataset, manually annotated using three different annotation schemes. We compare the annotations, analyze the inter-annotator agreement, and observe a number of interesting language-specific ...

This paper focuses on the modelling of the linguistic level of MICRO, a multi-agents speech understanding system largely inspired by cognitive models. It describes the cooperation between, on the one hand a syntactic parser using a Lexical Functional Grammar, and on the other hand an semantic analyser. The semantic analysis is achieved through a mechanism semantic priming carried out by a incre...

Do the production patterns of plural forms in noun-noun compounds reveal the workings of innate constraints that govern morphological processing? Gordon (1985) claims that the fact that children in elicitation tasks produce “rat-eater" but “mice-eater” to describe monsters that eat either rats or mice is evidence for a structural constraint on word formation that prevents regularly inflected fo...

Designing appropriate materials and activities to enhance vocabulary learning is one of the primary goals of language courses. Among the claims about efficient pedagogical tasks is the Involvement Load Hypothesis (Laufer & Hulstijn, 2001) according to which vocabulary development is contingent on the amount of cognitive process a task involves. Building on the previous research on this hypothes...

We present a new connectionist model of human spelling and investigate some of its properties. Although based on Sejnowski & Rosenberg’s (1987) NETtalk model of reading, it requires no pre-processing of the training data to align the phonemes and letters. The model achieves 100% performance on the training data (2837 monosyllabic words including many irregular words) and has a generalization pe...

According to the dual-route model, a printed string of letters can be processed by either a grapheme-to-phoneme conversion (GPC) route or a lexical-semantic route. Although meta-analyses of the imaging literature support the existence of distinct but interacting reading procedures, individual neuroimaging studies that explored neural correlates of reading yielded inconclusive results. We used a...

This thesis investigates computational approaches for analysing the semantic relations in compound nouns and other noun-noun constructions. Compound nouns in particular have received a great deal of attention in recent years due to the challenges they pose for natural language processing systems. One reason for this is that the semantic relation between the constituents of a compound is not exp...