Word Sense Disambiguation Based on Large Scale Polish CLARIN Heterogeneous Lexical ResourcesLexical resources can be applied in many different Natural Language Engineering tasks, but the most fundamental task is the recognition of word senses used in text contexts. The problem is difficult, not yet fully solved and different lexical resources provided varied support for it. Polish CLARIN lexical semantic resources are based on the plWordNet — a very large wordnet for Polish — as a central structure which is a basis for linking together several resources of different types. In this paper, several Word Sense Disambiguation (henceforth WSD) methods developed for Polish that utilise plWordNet are discussed. Textual sense descriptions in the traditional lexicon can be compared with text contexts using Lesk’s algorithm in order to find best matching senses. In the case of a wordnet, lexico-semantic relations provide the main description of word senses. Thus, first, we adapted and applied to Polish a WSD method based on the Page Rank. According to it, text words are mapped on their senses in the plWordNet graph and Page Rank algorithm is run to find senses with the highest scores. The method presents results lower but comparable to those reported for English. The error analysis showed that the main problems are: fine grained sense distinctions in plWordNet and limited number of connections between words of different parts of speech. In the second approach plWordNet expanded with the mapping onto the SUMO ontology concepts was used. Two scenarios for WSD were investigated: two step disambiguation and disambiguation based on combined networks of plWordNet and SUMO. In the former scenario, words are first assigned SUMO concepts and next plWordNet senses are disambiguated. In latter, plWordNet and SUMO are combined in one large network used next for the disambiguation of senses. The additional knowledge sources used in WSD improved the performance. The obtained results and potential further lines of developments were discussed.

No abstract

Introduction: The aim of this study was to determine the effect of deoxynivalenol (DON), given alone or with bentonite (which eliminates mycotoxicity) in the diet of mink dams throughout mating, pregnancy, and lactation period to pelt harvesting, on the mechanical properties and geometry of their long bones. Material and Methods: The minks were randomly assigned into two groups: a control group (not supplemented with DON, n = 15) and a group fed naturally DON-contaminated wheat and divided into three sub-groups (each sub-group n = 15), depending on bentonite dose: 0 M -sub-group fed naturally DONcontaminated wheat at a concentration of 3.7 mg kg -1 alone; 2 M -sub-group fed naturally DON-contaminated wheat at a concentration of 3.7 mg kg -1 and bentonite at a concentration of 2 kg 1000 kg -1 ; 0.5 M -sub-group fed naturally DONcontaminated wheat at a concentration of 3.7 mg kg -1 and bentonite at a concentration of 0.5 kg 1000 kg -1 . Results: The DON treatment reduced the length of the femur compared to the control group and reduced the bone weight dependently on the amount of bentonite supplementation. However, DON treatment reduced the MRWT and CI of the femur, irrespective of the bentonite supplementation, compared to the control. The total BTD and BMC decreased in all DON-treated groups (irrespective of the bentonite supplementation). Furthermore, the densitometric analysis showed that the main changes in BMD and BMC indicated bone loss in the proximal and distal parts of bone covering the trabecular bone; whereas when bentonite was given at the dose of 2 kg 1000 kg -1 an increase in the whole BMD and BMC was observed in the femoral midshaft. Conclusion: Analysis of the geometrical parameters seems to indicate that endosteal resorption was delayed after bentonite supplementation. The addition of bentonite diminished the DON action on bone homeostasis in the mink dams. Thus bentonite could prevent DON-induced bone loss in a dose-dependent manner.

In the paper we present an extended version of the graph-based unsupervised Word Sense Disambiguation algorithm. The algorithm is based on the spreading activation scheme applied to the graphs dynamically built on the basis of the text words and a large wordnet. The algorithm, originally proposed for English and Princeton WordNet, was adapted to Polish and plWordNet. An extension based on the knowledge acquired from the corpus-derived Measure of Semantic Relatedness was proposed. The extended algorithm was evaluated against the manually disambiguated corpus. We observed improvement in the case of the disambiguation performed for shorter text contexts. In addition the algorithm application expressed improvement in document clustering task.

Automatic Prompt System in the Process of Mapping plWordNet on Princeton WordNetThe paper offers a critical evaluation of the power and usefulness of an automatic prompt system based on the extended Relaxation Labelling algorithm in the process of (manual) mapping plWordNet on Princeton WordNet. To this end the results of manual mapping – that is inter-lingual relations between plWN and PWN synsets – are juxtaposed with the automatic prompts that were generated for the source language synsets to be mapped. We check the number and type of inter-lingual relations introduced on the basis of automatic prompts and the distance of the respective prompt synsets from the actual target language synsets.