This paper presents a model of the mental lexicon and its formation, based on the self-organizing neural network. When exposed to raw text, the model clusters words according to their semantic relatedness to form a semantic network 7]. Simulations using artiicial data are described that show how co-occurrence information can be used to create a low-dimensional representation of lexical semantic...

This paper develops a graph-theoretical model of text representation based on lexical chaining. Other than present approaches to chaining, this model reflects the logical document structure of texts as well as semantic relations of their lexical constituents in order to compute text similarity values. By varying the terminological ontology used to induce such relations, a door is opened to syst...

This paper introduces a new, graphbased view of the data of the FrameNet project, which we hope will make it easier to understand the mixture of semantic and syntactic information contained in FrameNet annotation. We show how English FrameNet and other Frame Semantic resources can be represented as sets of interconnected graphs of frames, frame elements, semantic types, and annotated instances ...

A study is reported of mathematical vocabulary and factual mathematical knowledge in PQ, a 22 year old with Down's syndrome (DS) who has a verbal mental age (MA) of 9 years 2 months and ST, a 15 year old with Williams syndrome (WS) who has a verbal MA of 9 years 6 months, matched to typically developing controls. The number of mathematical words contained within PQ's lexical stores was signific...

The lexical representation of words in Indo European languages is generally assumed to be driven by meaning compositionality. This study examined the lexical representation of complex verbs in German, which is a morphologically rich representative of Indo European languages. Three overt priming experiments manipulated prime target relations between morphological, semantic, and form relatedness....

Words with richer semantic representations are recognized faster across a range of lexical processing tasks. The most influential account of this finding is based on the idea that semantic richness effects are mediated by feedback from semantic-level to lower-level representations. In an earlier lexical decision study, Yap et al. (2015) tested this claim by examining the joint effects of stimul...

1. lntroducti(m Inlerlingual MT has tyl)ically come to incltLde a syntactic analysis of source language (SI ,) text followed hy its semm~tic interpretation ~.uld representation in terms of a text meaning representation (TMR) scheme, an interlin-gu,'t. Recently two distinct views of the nattzre of lhe inlerlingua have become current-one based on a worhl model (e.g., Nirenburg et al., 1992) and a...

The PASCAL RTE challenge has helped LCC to explore the applicability of enhancements that have been made to our logic form representation and WordNet lexical chains generator. Our system transforms each T-H pair into logic form representation with semantic relations. The system automatically generates NLP axioms serving as linguistic rewriting rules and lexical chain axioms that connect concept...

This dissertation examines the semantic underpinnings of argument realization. Much recent work in argument realization is based on some notion of “prominence preservation,” wherein the morphosyntactic prominence of an argument in the clause (e.g. its grammatical relation) supposedly reflects its prominence in the meaning of the clause. I explore prominence preservation as it applies to crossli...