Refine
Document Type
- Part of a Book (4) (remove)
Language
- English (4) (remove)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- Machine Learning (1)
- Maschinelles Lernen (1)
- Mustang District (1)
- Named Entity Changes (1)
- Namensänderungen (1)
- Nepal (1)
- Pflanzen (1)
- Pflanzengeographie (1)
- Pflanzensoziologie (1)
- Steppe (1)
Institute
- Universitätsbibliothek (4) (remove)
High impact events, political changes and new technologies are reflected in our language and lead to constant evolution of terms, expressions and names. Not knowing about names used in the past for referring to a named entity can severely decrease the performance of many computational linguistic algorithms. We propose NEER, an unsupervised method for named entity evolution recognition independent of external knowledge sources. We find time periods with high likelihood of evolution. By analyzing only these time periods using a sliding window co-occurrence method we capture evolving terms in the same context. We thus avoid comparing terms from widely different periods in time and overcome a severe limitation of existing methods for named entity evolution, as shown by the high recall of 90% on the New York Times corpus. We compare several relatedness measures for filtering to improve precision. Furthermore, using machine learning with minimal supervision improves precision to 94%.
We present a method for detecting word sense changes by utilizing automatically induced word senses. Our method works on the level of individual senses and allows a word to have e.g. one stable sense and then add a novel sense that later experiences change. Senses are grouped based on polysemy to find linguistic concepts and we can find broadening and narrowing as well as novel (polysemous and homonymic) senses. We evaluate on a testset, present recall and estimates of the time between expected and found change.
Im Zeitalter von Internet und digitaler Wissensvermittlung hat auch die Geschichtswissenschaft die Photographie als Quellenmaterial zur Dokumentation historischer Lebensbedingungen und Ereignisse schätzen gelernt. Neben dem geisteswissenschaftlichen Aspekt solcher Photodokumente gibt es einen technisch-konservatorischen Aspekt.
Kagbeni and its irrigated oasis are surrounded by subdesert dwarf scrubland. In the present study, a list of 78 species of vascular plants is presented for Kagbeni and its immediate surroundings, supplemented with data on the distribution of the species within the entire Mustan District. The data are arrived from own investigations and the geobotanical literature. A phytogeographical analysis shows the prevalence of western over eastern elements. Species with a wide distribution in Eurasia, which constitute one third of the total flora of Kagbeni, are of great importance as weeds on arable fields and in ruderal places within the irrigated oasis. Their occurrence is closely related to human activity. Presumably, most of these weeds have reached the area under study in connection with agriculture a long time ago. Weeds from the New World, although recorded in other villages of Mustan District, have not been found in Kagbeni. The weed vegetation of Kagbeni is documented by nine vegetation releves, and is compared to releves from Jomsom and Mzrpha. A floristic gradient from south to north that has been detected by earlier investigations throughout the whole district can be reproduced at the local scale. With regard to the weed flora, the effects of different crops are minimal, compared to effects of altitude and other factors related to altitude.