Not much is known about the linguistic resources other than discourse connectors for signalling coherence relations. We present here non discourse connector resources for marking coherence relations, namely “discourse verbs” and “discourse prepositions”. “Discourse verbs” are verbs such as precede or cause which take as arguments eventualities or facts. They enter into competition with discours...

Recent advances in distributional semantics combined with the availability of large-scale diachronic corpora offer new research avenues for the Digital Humanities. JESEME, the Jena Semantic Explorer, renders assistance to a non-technical audience to investigate diachronic semantic topics. JESEME runs as a website with query options and interactive visualizations of results, as well as a REST AP...

In this talk, we are going to give a systematic view of lexical semantics of Chinese language. From macro perspective point of view, lexical conceptual meanings are classified into hierarchical semantic types and each type plays some particular semantic functions of Host, Attribute, and Value to form a semantic compositional system. Lexical senses and their compositional functions will be exemp...

Current research being undertaken at both Cambridge and IBM is aimed at the construction of substantial lexicons containing lexical semantic information capable of use in automated natural language processing (NLP) applications. This work extends previous research on the semi-automatic extraction of lexical information from machine-readable versions of conventional dictionaries (MRDs) (see e.g....

But doing this requires fairly complex inference, because the words “block”, “enter”, “can”, “not” and “deliver” carve up the world in different ways.1 Words describe the world, so if we are going to draw the appropriate inferences in understanding a text, we must have underlying theories of aspects of the world and we must have axioms that link these to words. This includes domain-dependent kn...

In this paper, we consider the use of techniques that lead naturally towards using distributional lexical semantics for the automatic construction of corpora-specific stop word lists. We propose and evaluate a method for calculating stop words based on collocation, frequency information and comparisons of distributions within and across samples. This method is tested against the Enron email cor...

This paper investigates two types of meaning shift in composition. The first examines the well-known shifts in meaning in predications, known as coercions, that involve aspectual verbs like start, begin or finish or a verb like enjoy in combination with non-event denoting direct object arguments. The second involves the modifications of meaning that result from the application of an adjective m...

The systematic connection between English mass and count nouns has long been known. Those working within lexical semantics have frequently cited such systematic connections as instances which are susceptible of treatment by so-called lexical rules (Leech 1981), lexical inference rules (Ostler and Atkins 1991), or subtype coercion (Pustejovsky 1995). This paper has three aims: to present the pri...

DISLEX is an artiicial neural network model of the mental lexicon. It was built to test com-putationally whether the lexicon could consist of separate feature maps for the diierent lexical modalities and the lexical semantics, connected with ordered pathways. In the model, the ortho-graphic, phonological, and semantic feature maps and the associations between them are formed in an unsupervised ...