Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: tezaurus

Sortuj według:

Ogranicz wyniki do:

Innovative Training Practice in Electronics for Enterprises

100%

Raud Z. , Vodovozov V.

tom R. 88, nr 7b

166-170

An educational practice suitable for planning optimal staff training trajectories is described. Effective instruments are given to build professional thesauri and to find an institution capable of providing training in the frame of such thesauri. Using them, new knowledge and skills can be introduced, the contents of the corresponding disciplines refreshed, and the borders between the disciplines shifted fluently. This promotes designing the teaching modules in highly interdisciplinary areas and in the areas with specific needs.

W artykule opisano praktykę edukacyjną przydatną do optymalizowania formy i zakresu szkolenia personelu. Podano także skuteczne instrumenty do profesjonalnego budowania tezaurusów i sposobów znajdowania instytucji zdolnych do szkolenia w ramach takich tezaurusów. Tezaurusy mogą być uzupełniane o nową wiedzę i umiejętności, może być również odświeżana zawartość odpowiednich dyscyplin, a granice między dyscyplinami przesuwane płynnie. Sprzyja to projektowaniu modułów nauczania w dziedzinach wielodyscyplinarnych oraz na obszarach o szczególnych potrzebach.

Extending Word2Vec with domain-specific labels

67%

Švaňa M.

tom Vol. 30

157--160

Choosing a proper representation of textual data is an important part of natural language processing. One option is using Word2Vec embeddings, i.e., dense vectors whose properties can to a degree capture the “meaning” of each word. One of the main disadvantages of Word2Vec is its inability to distinguish between antonyms. Motivated by this deficiency, this paper presents a Word2Vec extension for incorporating domain-specific labels. The goal is to improve the ability to differentiate between embeddings of words associated with different document labels or classes. This improvement is demonstrated on word embeddings derived from tweets related to a publicly traded company. Each tweet is given a label depending on whether its publication coincides with a stock price increase or decrease. The extended Word2Vec model then takes this label into account. The user can also set the weight of this label in the embedding creation process. Experiment results show that increasing this weight leads to a gradual decrease in cosine similarity between embeddings of words associated with different labels. This decrease in similarity can be interpreted as an improvement of the ability to distinguish between these words.