Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952851098> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2952851098 abstract "In this paper we propose a novel neural approach for automatic decipherment of lost languages. To compensate for the lack of strong supervision signal, our model design is informed by patterns in language change documented in historical linguistics. The model utilizes an expressive sequence-to-sequence model to capture character-level correspondences between cognates. To effectively train the model in an unsupervised manner, we innovate the training procedure by formalizing it as a minimum-cost flow problem. When applied to the decipherment of Ugaritic, we achieve a 5.5% absolute improvement over state-of-the-art results. We also report the first automatic results in deciphering Linear B, a syllabic language related to ancient Greek, where our model correctly translates 67.3% of cognates." @default.
- W2952851098 created "2019-06-27" @default.
- W2952851098 creator A5010124873 @default.
- W2952851098 creator A5029740891 @default.
- W2952851098 creator A5086329948 @default.
- W2952851098 date "2019-06-16" @default.
- W2952851098 modified "2023-09-24" @default.
- W2952851098 title "Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B" @default.
- W2952851098 cites W1493923506 @default.
- W2952851098 cites W1523199077 @default.
- W2952851098 cites W1552968875 @default.
- W2952851098 cites W1728964438 @default.
- W2952851098 cites W2045009651 @default.
- W2952851098 cites W2115367993 @default.
- W2952851098 cites W2121745180 @default.
- W2952851098 cites W2136346830 @default.
- W2952851098 cites W2137766642 @default.
- W2952851098 cites W2140406733 @default.
- W2952851098 cites W2149823587 @default.
- W2952851098 cites W2172267041 @default.
- W2952851098 cites W2757281913 @default.
- W2952851098 cites W2762484717 @default.
- W2952851098 cites W2891081936 @default.
- W2952851098 cites W2891376302 @default.
- W2952851098 cites W2891745105 @default.
- W2952851098 cites W2963086938 @default.
- W2952851098 cites W2963260202 @default.
- W2952851098 cites W2963463964 @default.
- W2952851098 cites W2963993537 @default.
- W2952851098 cites W2964121744 @default.
- W2952851098 cites W342285082 @default.
- W2952851098 cites W764450821 @default.
- W2952851098 doi "https://doi.org/10.48550/arxiv.1906.06718" @default.
- W2952851098 hasPublicationYear "2019" @default.
- W2952851098 type Work @default.
- W2952851098 sameAs 2952851098 @default.
- W2952851098 citedByCount "1" @default.
- W2952851098 countsByYear W29528510982019 @default.
- W2952851098 crossrefType "posted-content" @default.
- W2952851098 hasAuthorship W2952851098A5010124873 @default.
- W2952851098 hasAuthorship W2952851098A5029740891 @default.
- W2952851098 hasAuthorship W2952851098A5086329948 @default.
- W2952851098 hasBestOaLocation W29528510981 @default.
- W2952851098 hasConcept C137293760 @default.
- W2952851098 hasConcept C138885662 @default.
- W2952851098 hasConcept C154945302 @default.
- W2952851098 hasConcept C194051139 @default.
- W2952851098 hasConcept C199360897 @default.
- W2952851098 hasConcept C204321447 @default.
- W2952851098 hasConcept C2778112365 @default.
- W2952851098 hasConcept C2778467380 @default.
- W2952851098 hasConcept C28490314 @default.
- W2952851098 hasConcept C41008148 @default.
- W2952851098 hasConcept C41895202 @default.
- W2952851098 hasConcept C48103436 @default.
- W2952851098 hasConcept C54355233 @default.
- W2952851098 hasConcept C86803240 @default.
- W2952851098 hasConceptScore W2952851098C137293760 @default.
- W2952851098 hasConceptScore W2952851098C138885662 @default.
- W2952851098 hasConceptScore W2952851098C154945302 @default.
- W2952851098 hasConceptScore W2952851098C194051139 @default.
- W2952851098 hasConceptScore W2952851098C199360897 @default.
- W2952851098 hasConceptScore W2952851098C204321447 @default.
- W2952851098 hasConceptScore W2952851098C2778112365 @default.
- W2952851098 hasConceptScore W2952851098C2778467380 @default.
- W2952851098 hasConceptScore W2952851098C28490314 @default.
- W2952851098 hasConceptScore W2952851098C41008148 @default.
- W2952851098 hasConceptScore W2952851098C41895202 @default.
- W2952851098 hasConceptScore W2952851098C48103436 @default.
- W2952851098 hasConceptScore W2952851098C54355233 @default.
- W2952851098 hasConceptScore W2952851098C86803240 @default.
- W2952851098 hasLocation W29528510981 @default.
- W2952851098 hasLocation W29528510982 @default.
- W2952851098 hasLocation W29528510983 @default.
- W2952851098 hasOpenAccess W2952851098 @default.
- W2952851098 hasPrimaryLocation W29528510981 @default.
- W2952851098 hasRelatedWork W142374489 @default.
- W2952851098 hasRelatedWork W1538473846 @default.
- W2952851098 hasRelatedWork W1563618553 @default.
- W2952851098 hasRelatedWork W1569841287 @default.
- W2952851098 hasRelatedWork W1803932089 @default.
- W2952851098 hasRelatedWork W2148757832 @default.
- W2952851098 hasRelatedWork W2351428524 @default.
- W2952851098 hasRelatedWork W2359001871 @default.
- W2952851098 hasRelatedWork W2374918184 @default.
- W2952851098 hasRelatedWork W3107474891 @default.
- W2952851098 isParatext "false" @default.
- W2952851098 isRetracted "false" @default.
- W2952851098 magId "2952851098" @default.
- W2952851098 workType "article" @default.