Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition
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 ar...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Slavic Studies, Polish Academy of Sciences
2020-12-01
|
| Series: | Cognitive Studies | Études cognitives |
| Subjects: | |
| Online Access: | https://journals.ispan.edu.pl/index.php/cs-ec/article/view/2325 |
| _version_ | 1797695262589714432 |
|---|---|
| author | Marek Maziarz Ewa Rudnicka |
| author_facet | Marek Maziarz Ewa Rudnicka |
| author_sort | Marek Maziarz |
| collection | DOAJ |
| description |
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.
|
| first_indexed | 2024-03-12T03:09:52Z |
| format | Article |
| id | doaj.art-0f3e03d9cbcc4fbaae2d562f9acf986f |
| institution | Directory Open Access Journal |
| issn | 2392-2397 |
| language | English |
| last_indexed | 2024-03-12T03:09:52Z |
| publishDate | 2020-12-01 |
| publisher | Institute of Slavic Studies, Polish Academy of Sciences |
| record_format | Article |
| series | Cognitive Studies | Études cognitives |
| spelling | doaj.art-0f3e03d9cbcc4fbaae2d562f9acf986f2023-09-03T14:28:53ZengInstitute of Slavic Studies, Polish Academy of SciencesCognitive Studies | Études cognitives2392-23972020-12-012010.11649/cs.2325Expanding WordNet with Gloss and Polysemy Links for Evocation Strength RecognitionMarek Maziarz0Ewa Rudnicka1Politechnika Wrocławska [Wrocław University of Science and Technology], WrocławPolitechnika Wrocławska [Wrocław University of Science and Technology], Wrocław 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. https://journals.ispan.edu.pl/index.php/cs-ec/article/view/2325evocationWordNetglossespolysemyevocation strengthsemantic relations |
| spellingShingle | Marek Maziarz Ewa Rudnicka Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition Cognitive Studies | Études cognitives evocation WordNet glosses polysemy evocation strength semantic relations |
| title | Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition |
| title_full | Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition |
| title_fullStr | Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition |
| title_full_unstemmed | Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition |
| title_short | Expanding WordNet with Gloss and Polysemy Links for Evocation Strength Recognition |
| title_sort | expanding wordnet with gloss and polysemy links for evocation strength recognition |
| topic | evocation WordNet glosses polysemy evocation strength semantic relations |
| url | https://journals.ispan.edu.pl/index.php/cs-ec/article/view/2325 |
| work_keys_str_mv | AT marekmaziarz expandingwordnetwithglossandpolysemylinksforevocationstrengthrecognition AT ewarudnicka expandingwordnetwithglossandpolysemylinksforevocationstrengthrecognition |