The current research explores the role of lexical representations and processing in the recognition of phonological variants. Two alternative approaches for variant recognition are considered: a representational approach that posits frequency-graded lexical representations for variant forms and inferential processes that mediate between the spoken variant and the lexical representation. In a le...

Document clustering is an unsupervised machine learning method that separates a large subject heterogeneous collection (Corpus) into smaller, more manageable, subject homogeneous collections (clusters). Traditional method of document clustering works around extracting textual features like: terms, sequences, and phrases from documents. These features are independent of each other and do not cat...

This thesis mainly concerns itself with the issue of semantic similarity and computational applications of it. Semantic similarity has for a long time been a subject of intense scholarship in the fields of Artificial Intelligence, Psychology and Cognitive Science. Computational models trying to imitate aspects of this cognitive ability date back to Quillian and his spreading activation algorith...

Accurately representing synonymy using distributional similarity requires large volumes of data to reliably represent infrequent words. However, the naı̈ve nearest-neighbour approach to compare context vectors extracted from large corpora scales poorly. The Spatial Approximation Sample Hierarchy (SASH) is a data-structure for performing approximate nearest-neighbour queries, and has been previou...

We describe our participation in the PASCAL-2005 Recognizing Textual Entailment Challenge. Our method is based on calculating “directed” sentence similarity: checking the directed “semantic” word overlap between the text and the hypothesis. We use frequency-based term weighting in combination with two different lexical similarity measures. Our best run shows 0.55 accuracy on the test data, alth...

Distributional word similarity is most commonly perceived as a symmetric relation. Yet, one of its major applications is lexical expansion, which is generally asymmetric. This paper investigates the nature of directional (asymmetric) similarity measures, which aim to quantify distributional feature inclusion. We identify desired properties of such measures, specify a particular one based on ave...

Techniques that exploit knowledge of distributional similarity between words have been proposed in many areas of Natural Language Processing. For example, in language modeling, the sparse data problem can be alleviated by estimating the probabilities of unseen co-occurrences of events from the probabilities of seen co-occurrences of similar events. In other applications, distributional similari...

ABSTARCT: Paraphrase is a process of computing the semantic similarity between sentences, which are not lexicographically similar. Though a number of metrics for English language have been proposed in literature, to quantify textual similarity; it addresses the problem for detection of monolingual text-text lexical similarity. Existing system for Indian Language paraphrase detection uses lexica...

In this article we present an approach to the automatic discovery of term similarities, which may serve as a basis for a number of term-oriented knowledge mining tasks. The method for term comparison combines internal (lexical similarity) and two types of external criteria (syntactic and contextual similarities). Lexical similarity is based on sharing lexical constituents (i.e. term heads and m...

A new metaphor of two-dimensional text for data-driven semantic modeling of natural language is proposed, which provides an entirely new angle on the representation of text: not only syntagmatic relations are annotated in the text, but also paradigmatic relations are made explicit by generating lexical expansions. We operationalize dis-tributional similarity in a general framework for large cor...