Word Sense Disambiguation Using Prior Probability Estimation Based on the Korean WordNet

Supervised disambiguation using a large amount of corpus data delivers better performance than other word sense disambiguation methods. However, it is not easy to construct large-scale, sense-tagged corpora since this requires high cost and time. On the other hand, implementing unsupervised disambiguation is relatively easy, although most of the efforts have not been satisfactory. A primary reason for the performance degradation of unsupervised disambiguation is that the semantic occurrence probability of ambiguous words is not available. Hence, a data deficiency problem occurs while determining the dependency between words. This paper proposes an unsupervised disambiguation method using a prior probability estimation based on the Korean WordNet. This performs better than supervised disambiguation. In the Korean WordNet, all the words have similar semantic characteristics to their related words. Thus, it is assumed that the dependency between words is the same as the dependency between their related words. This resolves the data deficiency problem by determining the dependency between words by calculating the χ2 statistic between related words. Moreover, in order to have the same effect as using the semantic occurrence probability as prior probability, which is used in supervised disambiguation, semantically related words of ambiguous vocabulary are obtained and utilized as prior probability data. An experiment was conducted with Korean, English, and Chinese to evaluate the performance of our proposed lexical disambiguation method. We found that our proposed method had better performance than supervised disambiguation methods even though our method is based on unsupervised disambiguation (using a knowledge-based approach).

Statistical estimation of container condensation in marine transportation between Far East Asia and Europe

Condensation inside marine containers occurs during voyages owing to weather changes. In this study, we define the condensation probability along one of the major routes for container ships between Asia and Europe. First, the inside and outside air conditions were measured on land in Japan, and a correlation analysis was conducted to derive their relationship. Second, onboard measurements were conducted for 20,000 twenty-foot equivalent unit (TEU) ships to determine the variation in outside air conditions. Complicated patterns of weather change were observed with changes in latitude, sea area, and season. Third, condensation probability was estimated based on a multi-regression analysis with land and onboard measured data. The maximum condensation probability in westbound or eastbound voyages in winter was found to be approximately 50%. The condensation probability estimation method established in this study can contribute to the quantification of cargo damage risks for the planning of marine container transportation voyages.