Matches in SemOpenAlex for { <https://semopenalex.org/work/W2787883929> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2787883929 abstract "We present an in-depth analysis of four popular word embeddings (Word2Vec, GloVe, fastText and Paragram) in terms of their semantic compositionality. In addition, we propose a method to tune these embeddings towards better compositionality. We find that training the existing embeddings to compose lexicographic definitions improves their performance in this task significantly, while also getting similar or better performance in both word similarity and sentence embedding evaluations. Our method tunes word embeddings using a simple neural network architecture with definitions and lemmas from WordNet. Since dictionary definitions are semantically similar to their associated lemmas, they are the ideal candidate for our tuning method, as well as evaluating for compositionality. Our architecture allows for the embeddings to be composed using simple arithmetic operations, which makes these embeddings specifically suitable for production applications such as web search and data mining. We also explore more elaborate and involved compositional models. In our analysis, we evaluate original embeddings, as well as tuned embeddings, using existing word similarity and sentence embedding evaluation methods. Aside from these evaluation methods used in related work, we also evaluate embeddings using a ranking method which tests composed vectors using the lexicographic definitions already mentioned. In contrast to other evaluation methods, ours is not invariant to the magnitude of the embedding vector, which we show is important for composition. We consider this new evaluation method, called CompVecEval, to be a key contribution." @default.
- W2787883929 created "2018-03-06" @default.
- W2787883929 creator A5002625178 @default.
- W2787883929 creator A5042240343 @default.
- W2787883929 creator A5055639036 @default.
- W2787883929 date "2018-01-01" @default.
- W2787883929 modified "2023-09-23" @default.
- W2787883929 title "Improving Word Embedding Compositionality using Lexicographic Definitions" @default.
- W2787883929 cites W1567378137 @default.
- W2787883929 cites W1814992895 @default.
- W2787883929 cites W1832693441 @default.
- W2787883929 cites W1854884267 @default.
- W2787883929 cites W2037959956 @default.
- W2787883929 cites W2054045793 @default.
- W2787883929 cites W2064675550 @default.
- W2787883929 cites W2067438047 @default.
- W2787883929 cites W2070246124 @default.
- W2787883929 cites W2113640060 @default.
- W2787883929 cites W2117130368 @default.
- W2787883929 cites W2131774270 @default.
- W2787883929 cites W2311143338 @default.
- W2787883929 cites W2963366649 @default.
- W2787883929 cites W2963502184 @default.
- W2787883929 doi "https://doi.org/10.1145/3178876.3186007" @default.
- W2787883929 hasPublicationYear "2018" @default.
- W2787883929 type Work @default.
- W2787883929 sameAs 2787883929 @default.
- W2787883929 citedByCount "16" @default.
- W2787883929 countsByYear W27878839292018 @default.
- W2787883929 countsByYear W27878839292019 @default.
- W2787883929 countsByYear W27878839292020 @default.
- W2787883929 countsByYear W27878839292021 @default.
- W2787883929 countsByYear W27878839292022 @default.
- W2787883929 crossrefType "proceedings-article" @default.
- W2787883929 hasAuthorship W2787883929A5002625178 @default.
- W2787883929 hasAuthorship W2787883929A5042240343 @default.
- W2787883929 hasAuthorship W2787883929A5055639036 @default.
- W2787883929 hasBestOaLocation W27878839291 @default.
- W2787883929 hasConcept C114614502 @default.
- W2787883929 hasConcept C121375916 @default.
- W2787883929 hasConcept C138885662 @default.
- W2787883929 hasConcept C154945302 @default.
- W2787883929 hasConcept C159254197 @default.
- W2787883929 hasConcept C199360897 @default.
- W2787883929 hasConcept C204321447 @default.
- W2787883929 hasConcept C2777462759 @default.
- W2787883929 hasConcept C33923547 @default.
- W2787883929 hasConcept C41008148 @default.
- W2787883929 hasConcept C41608201 @default.
- W2787883929 hasConcept C41895202 @default.
- W2787883929 hasConcept C90805587 @default.
- W2787883929 hasConceptScore W2787883929C114614502 @default.
- W2787883929 hasConceptScore W2787883929C121375916 @default.
- W2787883929 hasConceptScore W2787883929C138885662 @default.
- W2787883929 hasConceptScore W2787883929C154945302 @default.
- W2787883929 hasConceptScore W2787883929C159254197 @default.
- W2787883929 hasConceptScore W2787883929C199360897 @default.
- W2787883929 hasConceptScore W2787883929C204321447 @default.
- W2787883929 hasConceptScore W2787883929C2777462759 @default.
- W2787883929 hasConceptScore W2787883929C33923547 @default.
- W2787883929 hasConceptScore W2787883929C41008148 @default.
- W2787883929 hasConceptScore W2787883929C41608201 @default.
- W2787883929 hasConceptScore W2787883929C41895202 @default.
- W2787883929 hasConceptScore W2787883929C90805587 @default.
- W2787883929 hasLocation W27878839291 @default.
- W2787883929 hasLocation W27878839292 @default.
- W2787883929 hasOpenAccess W2787883929 @default.
- W2787883929 hasPrimaryLocation W27878839291 @default.
- W2787883929 hasRelatedWork W2293834552 @default.
- W2787883929 hasRelatedWork W2573169100 @default.
- W2787883929 hasRelatedWork W2806906294 @default.
- W2787883929 hasRelatedWork W2949267551 @default.
- W2787883929 hasRelatedWork W2993300079 @default.
- W2787883929 hasRelatedWork W3086845375 @default.
- W2787883929 hasRelatedWork W3107679445 @default.
- W2787883929 hasRelatedWork W3146034405 @default.
- W2787883929 hasRelatedWork W3158961393 @default.
- W2787883929 hasRelatedWork W4294875713 @default.
- W2787883929 isParatext "false" @default.
- W2787883929 isRetracted "false" @default.
- W2787883929 magId "2787883929" @default.
- W2787883929 workType "article" @default.