Recognizing analogies, synonyms, antonyms, and associations appear to be four distinct tasks, requiring distinct NLP algorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four semantic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algorithms for each semantic phenome...

Elicitation Materials. Subjects were given the same set of disyllabic real words in both English and Spanish in carrier phrases, which made the tokens closer to natural speech. This maintained control and comparability of the segments in the same environment, since vowel height and syllabic stress are known to affect aspiration (Keating, 1983). The English carrier phrase was "Say the word ___ag...

One problem in the design of a lexicon for natural language processing is the representation of semantic knowledge. We examine the adequacy of knowledge representation formalisms developed in artificial intelligence, in particular of term subsumption languages for these issues. In order to derive some basic requirements for a suitable representation language we analyze a number of definitions o...

We propose a model for providing integrated and uniied access to multiple information sources. Each source comprises: (a) an ontology i.e. a set of terms structured by a subsumption relation, and (b) a database that stores descriptions of objects using terms of the ontol-ogy. We assume that diierent sources may use diierent ontologies, i.e., diierent terminologies with terms that correspond to ...

In the finite-state temporality approach, events in natural language semantics have been characterized in regular languages, with strings representing sequences of temporal observations. We extend this approach to natural language constructions which are not regular. Context-free constructions are detailed and discussed. Superposition, the key operator in the finite-state temporality approach i...

A proposal for text mining as a support for knowledge discovery on biological descriptions is introduced. Our aim is both to sustain the curation of databases and to offer an alternative representation frame for accessing information in the biodiversity domain. We works on raw texts with minimum human intervention, applying natural language processing to integrate linguistic and domain knowledg...

Paraphrases and other semantically related sentences present a challenge to NLP and IR applications such as multi-document sum-marization and question answering systems. While it is generally agreed that paraphrases contain approximately equivalent ideas, they often diier from one another in subtle, yet non-trivial, ways. In this paper, we examine semantic diierences in cases of paraphrase and ...

Taxonomic case-based reasoning is a conversational casebased reasoning methodology that employs feature subsumption taxonomies for incremental case retrieval. Although this approach has several benefits over standard retrieval approaches, methods for automatically acquiring these taxonomies from text documents do not exist, which limits its widespread implementation. To accelerate and simplify ...