xcit'ed

Statistical association measures have been widely applied in information retrieval research, usually employing a clustering of documents or terms on the basis of their relationships. Applications of the association measures for term clustering include automatic thesaurus construction and query expansion. This research evaluates the similarity of six association measures by comparing the relationship and behavior they demonstrate in various analyses of a test corpus. Analysis techniques include comparisons of highly ranked termpairs and term clusters, analyses of the correlation among the association measures using Pearson’s correlation coefficient and MDS mapping, and an analysis of the impact of a term frequency on the association values by means of z-score. The major findings of the study are as follows: First, the most similar association measures are mutual information and Yule’s coefficient of colligation Y, whereas cosine and Jaccard coefficients, as well as x2 statistic and likelihood ratio, demonstrate quite similar behavior for terms with high frequency. Second, among all the measures, the x2 statistic is the least affected by the frequency of terms. Third, although cosine and Jaccard coefficients tend to emphasize high frequency terms, mutual information and Yule’s Y seem to overestimate rare terms.

Abstract. This paper explores different strategies for extracting similarity relations between words from partially parsed text corpora. The strategies we have analysed do not require supervised training nor semantic information available from general lexical resources. They differ in the amount and the quality of the syntactic contexts against which words are compared. The paper presents in details the notion of syntactic context and how syntactic information could be used to extract semantic regularities of word sequences. Finally, experimental tests with Portuguese corpus demonstrate that similarity measures based on fine-grained and elaborate syntactic contexts perform better than those based on poorly defined contexts.

We propose a method to build thesauri on the basis of grammatical relations. The proposed method constructs thesauri by using a hierarchical clustering algorithm. An important point in this paper is the claim that thesauri in order to be efficient need to take (surface) case information into account. We refer to the thesauri as "relation-based thesaurus (RBT)." In the experiment, four RBTs of Japanese nouns were constructed from 26,023 verb-noun co-occurrences, and each RBT was evaluated by objective criteria. The experiment has shown that the RBTs have better properties for selectional restriction of case frames than conventional ones.

The term word association is used in a very particular sense in the p!ycholinguistic literature. (Generally speaking, subjects respond quicker than normal to the word "nurse" if it follows a highly associated word such as "doctor.") We will extend the term to provide the basis for a statistical description of a variety of interesting linguistic phenomena, ranging from semantic rehtions of the doctor/nurse type (content word/content word) to lexico-syntactlc co-occurrence constraints between

Abstract: Context is used in many NLP systems as an indicator of a term's syntactic and semantic function. The accuracy of the system is dependent on the quality and quantity of contextual information available to describe each term. However, the quantity variable is no longer fixed by limited corpus resources. Given fixed training time and computational resources, it makes sense for systems to invest time in extracting high quality contextual information from a fixed corpus. However, with an effectively limitless quantity of text available, extraction rate and representation size need to be considered. We use thesaurus extraction with a range of context extracting tools to demonstrate the interaction between context quantity, time and size on a corpus of 300 million words.

Abstract: A method of determining the similarity of nouns on the basis of a metric derived from the distribution of subject, verb and object in a large text corpus is described. The resulting quasi-semantic classification of nouns demonstrates the plausibility of the distributional hypothesis, and has potential application to a variety of tasks, including automatic indexing, resolving nominal compounds, and determining the scope of modification.

Abstract. Is it possible to discover semantic term relations useful for thesauri without any semantic information? Yes, it is. A recent approach for automatic thesaurus construction is based on explicit linguistic knowledge, i.e. a domain independent parser without any semantic component and implicit linguistic knowledge contained in large amounts of real world texts. Such texts include implicitly the linguistic, especially semantic knowledge that the authors needed for formulating their texts. This article explains how implicit semantic knowledge can be transformed to an explicit one. Evaluations of quality and performance of the approach are very encouraging.

Abstract: Bootstrapping semantics from text is one of the greatest challenges in natural language learning. We first define a word similarity measure based on the distributional pattern of words. The similarity measure allows us to construct a thesaurus using a parsed corpus. We then present a new evaluation methodology for the automatically constructed thesaurus. The evaluation results show that the thesaurus is significantly closer to WordNet than Roget Thesaurus is.

Abstract: We describe and evaluate experimentally a method for clustering words according to their distribution in particular syntactic contexts. Words are represented by the relative frequency distributions of contexts in which they appear, and relative entropy between those distributions is used as the similarity measure for clustering. Clusters are represented by average context distributions derived from the given words according to their probabilities of cluster membership. In many cases, the clusters can be thought of as encoding coarse sense distinctions. Deterministic annealing is used to find lowest distortion sets of clusters: as the annealing parameter increases, existing clusters become unstable and subdivide, yielding a hierarchical "soft" clustering of the data. Clusters are used as the basis for class models of word coocurrence, and the models evaluated with respect to held-out test data.