Matches in SemOpenAlex for { <https://semopenalex.org/work/W4300868045> ?p ?o ?g. }
Showing items 1 to 51 of
51
with 100 items per page.
- W4300868045 abstract "Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector spaces to align them such that similar words are mapped to each other. We show empirically that the performance of bilingual correspondents learned using our proposed unsupervised method is comparable to that of using supervised bilingual correspondents from a seed dictionary." @default.
- W4300868045 created "2022-10-04" @default.
- W4300868045 creator A5002602581 @default.
- W4300868045 creator A5037740212 @default.
- W4300868045 creator A5038581447 @default.
- W4300868045 date "2017-12-19" @default.
- W4300868045 modified "2023-09-26" @default.
- W4300868045 title "Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings" @default.
- W4300868045 doi "https://doi.org/10.48550/arxiv.1712.06961" @default.
- W4300868045 hasPublicationYear "2017" @default.
- W4300868045 type Work @default.
- W4300868045 citedByCount "0" @default.
- W4300868045 crossrefType "posted-content" @default.
- W4300868045 hasAuthorship W4300868045A5002602581 @default.
- W4300868045 hasAuthorship W4300868045A5037740212 @default.
- W4300868045 hasAuthorship W4300868045A5038581447 @default.
- W4300868045 hasBestOaLocation W43008680451 @default.
- W4300868045 hasConcept C138885662 @default.
- W4300868045 hasConcept C154945302 @default.
- W4300868045 hasConcept C165696696 @default.
- W4300868045 hasConcept C204321447 @default.
- W4300868045 hasConcept C2779235283 @default.
- W4300868045 hasConcept C38652104 @default.
- W4300868045 hasConcept C41008148 @default.
- W4300868045 hasConcept C41895202 @default.
- W4300868045 hasConcept C90805587 @default.
- W4300868045 hasConceptScore W4300868045C138885662 @default.
- W4300868045 hasConceptScore W4300868045C154945302 @default.
- W4300868045 hasConceptScore W4300868045C165696696 @default.
- W4300868045 hasConceptScore W4300868045C204321447 @default.
- W4300868045 hasConceptScore W4300868045C2779235283 @default.
- W4300868045 hasConceptScore W4300868045C38652104 @default.
- W4300868045 hasConceptScore W4300868045C41008148 @default.
- W4300868045 hasConceptScore W4300868045C41895202 @default.
- W4300868045 hasConceptScore W4300868045C90805587 @default.
- W4300868045 hasLocation W43008680451 @default.
- W4300868045 hasOpenAccess W4300868045 @default.
- W4300868045 hasPrimaryLocation W43008680451 @default.
- W4300868045 hasRelatedWork W142374489 @default.
- W4300868045 hasRelatedWork W1483367581 @default.
- W4300868045 hasRelatedWork W1508636238 @default.
- W4300868045 hasRelatedWork W1588912689 @default.
- W4300868045 hasRelatedWork W2002275558 @default.
- W4300868045 hasRelatedWork W2097662711 @default.
- W4300868045 hasRelatedWork W2102203038 @default.
- W4300868045 hasRelatedWork W2390581343 @default.
- W4300868045 hasRelatedWork W2735335964 @default.
- W4300868045 hasRelatedWork W31012516 @default.
- W4300868045 isParatext "false" @default.
- W4300868045 isRetracted "false" @default.
- W4300868045 workType "article" @default.