In this paper we introduce ProThes, a system for focused Web information retrieval. ProThes combines three approaches: metasearch, advanced graphical user interface (GUI) for query specification, and thesaurusbased query techniques. ProThes attempts to employ domain-specific knowledge, which is represented by a conceptual thesaurus. Moreover, ProThes uses domain-specific results ranking heurist...

In this paper we present the approach of introducing thesaurus knowledge into probabilistic topic models. The main idea of the approach is based on the assumption that the frequencies of semantically related words and phrases, which are met in the same texts, should be enhanced: this action leads to their larger contribution into topics found in these texts. We have conducted experiments with s...

A lattice-based model for information retrieval has been suggested in the 1960’s but has been seen as a theoretical possibility hard to practically apply ever since. This paper attempts to revive the lattice model and demonstrate its applicability in an information retrieval system, FaIR, that incorporates a graphical representation of a faceted thesaurus. It shows how Boolean queries can be la...

We propose a novel method to construct semantic orientation lexicons using large data and a thesaurus. To deal with large data, we use Count-Min sketch to store the approximate counts of all word pairs in a bounded space of 8GB. We use a thesaurus (like Roget) to constrain near-synonymous words to have the same polarity. This framework can easily scale to any language with a thesaurus and a unz...

To enhance the technology for computing semantic equivalence, we introduce the notion of phrasal thesaurus which is a natural extension of conventional word-based thesaurus. Among a variety of phrases that conveys the same meaning, i.e., paraphrases, we focus on syntactic variants that are compositionally explainable using a small number of atomic knowledge, and develop a system which dynamical...

This paper describes our participation in the BioASQ semantic indexing challenge with two hierarchical text categorization systems. Both systems originated from previous research in thesaurus topic assignment applied on small domains from the legal document management field. One of the described systems employs a classical top-down approach based on a collection of local classifiers. The other ...

Foodand human nutrition-related subject headings or descriptors of the following thesauri-databases are assessed: NAL Thesaurus/Agricola, Agrovoc/Agris, CAB Thesaurus, FSTA Thesaurus, MeSH/Medline. Food concepts can be represented by thousands of different terms but subject scope of a particular term is sometimes vague. There exist important differences among thesauri regarding same or similar ...

The paper aims at providing a description of EARTh, the Environmental Application Reference Thesaurus. It represents a common general thesaurus for the environment, which has been published as a SKOS dataset in the Linked Open Data cloud. It promises to become a core tool for indexing and discovery environmental resources by refining and extending GEMET, which is considered the de facto standar...

Diana McCarthy et al. (ACL-2004) obtain the predominant sense for an ambiguous word based on a weighted thesaurus of words related to the ambiguous word. This thesaurus is obtained using Dekang Lin’s (COLING-ACL1998) distributional similarity method. Lin averages the distributional similarity by the whole training corpus; thus the list of words related to a given word in his thesaurus is given ...