Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel framework for constructing semantic spaces that take syntactic relations into account. We introduce a formalization for this class of models which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art. 1.

NLP methods and applications need to take account not only of “classical ” lexical relations, as found in WordNet, but the lessstructural, more context-dependent “nonclassical” relations that readers intuit in text. In a reader-based study of lexical relations in text, most were found to be of the latter type. The relationships themselves are analyzed, and consequences for NLP are discussed. 1

Abstract not found

A central concern of psycholinguistic research is explaining the relative ease or difficulty involved in processing words. In this thesis, we explore the connection between lexical processing effort and measurable properties of the linguistic environment. Distributional information (information about a word's contexts of use) is easily extracted from large language corpora in the form of co-occurrence statistics. We claim that such simple distributional statistics can form the basis of a parsimonious model of lexical processing effort.

Traditional vector-based models use word co-occurrence counts from large corpora to represent lexical meaning. In this paper we present a novel approach for constructing semantic spaces that takes syntactic relations into account. We introduce a formalisation for this class of models and evaluate their adequacy on two modelling tasks: semantic priming and automatic discrimination of lexical relations.

A reader's perception of even an "objective" text is to some degree subjective. We present the results of a pilot study in which we looked at the degree of subjectivity in readers' perceptions of lexical semantic relations, which are the building blocks of the lexical chains used in many applications in natural language processing. An example is presented in which the subjectivity reflects the reader's attitude.

this paper: multi-word idioms (Great minds think alike, Til the cows come home) and common word combinations (last chance, faced with, good job).

A fundamental question in research on conceptual structure concerns how information is represented in memory and used in tasks such as recognizing words. The present research focused on the role of correlations among semantic properties in conceptual memory. Norms were collected for 190 entities from 10 categories. Property intercorrelations influenced people's performance in both a property verification task and a short interval semantic priming experiment. Furthermore, correlated properties were more important for biological kinds than for artifacts. A connectionist model of the computation of word meaning was implemented in which property intercorrelations developed in the course of learning. The model was used to simulate the results of the two experiments. We then tested a novel prediction derived from the model: that the intercorrelational density of a concept's properties should influence the speed with which a concept is computed. This prediction was confirmed in a final experi...

Abstract: An analysis of linguistic approaches to determining the lexical cohesion in text reveals differences in the types of lexical semantic relations (term relationships) that contribute to the continuity of lexical meaning in the text. Differences were also found in how these lexical relations join words together, sometimes with grammatical relations, to form larger groups of related words that sometimes exhibit a more tightly-knit internal structure than a simple chain of words. Further analysis of the lexical semantic relations indicates a specific need to focus on a neglected group of relations, referred to as nonclassical relations, and a general need to focus on relations in the context of text. Experiments with human readers of text are suggested to investigate these issues, as well as address the lack of research that uses human subjects to identify reader-oriented relations. Because lexical cohesion contributes to the semantic understanding of text, these reader-oriented relations have potential relevance to improving access to text-based information. As well, the structured groups of words formed using a combination of lexical and grammatical relations has potential computational benefits to lexical cohesion analysis of text. 1.

This paper considers how fluent language users are rational in their language processing, their unconscious language representation systems optimally prepared for comprehension and production, how language learners are intuitive statisticians, and how acquisition can be understood as contingency learning. But there are important aspects of second language acquisition that do not appear to be rational, where input fails to become intake. The paper describes the types of situation where cognition deviates from rationality and it introduces how the apparent irrationalities of L2 acquisition result from standard phenomena of associative learning as encapsulated in the models of Rescorla and Wagner (1972) and Cheng and Holyoak (1995), which describe how cue salience, outcome importance, and the history of learning from multiple probabilistic cues affect the development of ‘learned selective attention’ and transfer. This article considers how fluent language users are rational in their language processing, rational in the sense that their unconscious language representation