Mechanisms of Polysemy

According to George K. Zipf, more frequent words have more senses. We have tested this law using corpora and wordnets of English, Spanish, Portuguese, French, Polish, Japanese, Indonesian and Chinese. We have proved that the law works pretty well for all of these languages if we take - as Zipf did - mean values of meaning count and averaged ranks. On the other hand, the law disastrously fails in predicting the number of senses for a single lemma. We have also provided the evidence that slope coefficients of Zipfian log-log linear model may vary from language to language.

In this paper we present a new individual measure for the task of evocation strength prediction. The proposed solution is based on Dijkstra’s distances calculated on the WordNet graph expanded with polysemy relations. The polysemy network was constructed using chaining procedure executed on individual word senses of polysemous lemmas. We show that the shape of polysemy associations between WordNet senses has a positive impact on evocation strength prediction and the measure itself could be successfully reused in more complex ML frameworks.

Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition Evocation – a phenomenon of sense associations going beyond standard (lexico)-semantic relations – is difficult to recognise for natural language processing systems. Machine learning models give predictions which are only moderately correlated with the evocation strength. It is believed that ordinary graph measures are not as good at this task as methods based on vector representations. The paper proposes a new method of enriching the WordNet structure with weighted polysemy and gloss links, and proves that Dijkstra’s algorithm performs equally as well as other more sophisticated measures when set together with such expanded structures. Rozszerzenie WordNetu o glosy i relacje polisemiczne na potrzeby rozpoznawania siły ewokacji Ewokacja – zjawisko skojarzeń zmysłowych wykraczających poza standardowe (leksykalne) relacje semantyczne – jest trudne do rozpoznania dla systemów przetwarzania języka naturalnego. Modele uczenia maszynowego dają prognozy tylko umiarkowanie skorelowane z siłą ewokacji. Uważa się, że zwykłe miary grafowe nie są tak dobre w tym zadaniu, jak metody oparte na reprezentacjach wektorowych. Proponujemy nową metodę wzbogacania struktury WordNet o polisemie ważone i linki połysku i udowadniamy, że algorytm Dijkstry zestawiony z tak rozbudowanymi strukturami działa a także inne, bardziej wyrafinowane środki.