Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014010584> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3014010584 abstract "For endangered languages, data collection campaigns have to accommodate the challenge that many of them are from oral tradition, and producing transcriptions is costly. Therefore, it is fundamental to translate them into a widely spoken language to ensure interpretability of the recordings. In this paper we investigate how the choice of translation language affects the posterior documentation work and potential automatic approaches which will work on top of the produced bilingual corpus. For answering this question, we use the MaSS multilingual speech corpus (Boito et al., 2020) for creating 56 bilingual pairs that we apply to the task of low-resource unsupervised word segmentation and alignment. Our results highlight that the choice of language for translation influences the word segmentation performance, and that different lexicons are learned by using different aligned translations. Lastly, this paper proposes a hybrid approach for bilingual word segmentation, combining boundary clues extracted from a non-parametric Bayesian model (Goldwater et al., 2009a) with the attentional word segmentation neural model from Godard et al. (2018). Our results suggest that incorporating these clues into the neural models' input representation increases their translation and alignment quality, specially for challenging language pairs." @default.
- W3014010584 created "2020-04-03" @default.
- W3014010584 creator A5040820339 @default.
- W3014010584 creator A5043744108 @default.
- W3014010584 creator A5053823442 @default.
- W3014010584 date "2020-05-11" @default.
- W3014010584 modified "2023-09-24" @default.
- W3014010584 title "Investigating Language Impact in Bilingual Approaches for Computational Language Documentation" @default.
- W3014010584 cites W1557247526 @default.
- W3014010584 cites W1563026167 @default.
- W3014010584 cites W175497273 @default.
- W3014010584 cites W2038542953 @default.
- W3014010584 cites W2101105183 @default.
- W3014010584 cites W2101281673 @default.
- W3014010584 cites W2111668269 @default.
- W3014010584 cites W2122228338 @default.
- W3014010584 cites W2126377586 @default.
- W3014010584 cites W2126449874 @default.
- W3014010584 cites W2347145335 @default.
- W3014010584 cites W240478693 @default.
- W3014010584 cites W2466918907 @default.
- W3014010584 cites W2515167330 @default.
- W3014010584 cites W2586602577 @default.
- W3014010584 cites W2762715843 @default.
- W3014010584 cites W2808682925 @default.
- W3014010584 cites W2883972335 @default.
- W3014010584 cites W2895097770 @default.
- W3014010584 cites W2949328740 @default.
- W3014010584 cites W2950228150 @default.
- W3014010584 cites W2955019563 @default.
- W3014010584 cites W2963378435 @default.
- W3014010584 cites W2963819008 @default.
- W3014010584 cites W2964308564 @default.
- W3014010584 cites W2977997709 @default.
- W3014010584 cites W2980433540 @default.
- W3014010584 cites W3032598645 @default.
- W3014010584 cites W2173413395 @default.
- W3014010584 cites W2586232309 @default.
- W3014010584 hasPublicationYear "2020" @default.
- W3014010584 type Work @default.
- W3014010584 sameAs 3014010584 @default.
- W3014010584 citedByCount "0" @default.
- W3014010584 crossrefType "proceedings-article" @default.
- W3014010584 hasAuthorship W3014010584A5040820339 @default.
- W3014010584 hasAuthorship W3014010584A5043744108 @default.
- W3014010584 hasAuthorship W3014010584A5053823442 @default.
- W3014010584 hasBestOaLocation W30140105841 @default.
- W3014010584 hasConcept C199360897 @default.
- W3014010584 hasConcept C204321447 @default.
- W3014010584 hasConcept C41008148 @default.
- W3014010584 hasConcept C56666940 @default.
- W3014010584 hasConceptScore W3014010584C199360897 @default.
- W3014010584 hasConceptScore W3014010584C204321447 @default.
- W3014010584 hasConceptScore W3014010584C41008148 @default.
- W3014010584 hasConceptScore W3014010584C56666940 @default.
- W3014010584 hasLocation W30140105841 @default.
- W3014010584 hasLocation W30140105842 @default.
- W3014010584 hasLocation W30140105843 @default.
- W3014010584 hasOpenAccess W3014010584 @default.
- W3014010584 hasPrimaryLocation W30140105841 @default.
- W3014010584 hasRelatedWork W1541967140 @default.
- W3014010584 hasRelatedWork W2109507516 @default.
- W3014010584 hasRelatedWork W2112962394 @default.
- W3014010584 hasRelatedWork W2118300983 @default.
- W3014010584 hasRelatedWork W2166247150 @default.
- W3014010584 hasRelatedWork W2740990710 @default.
- W3014010584 hasRelatedWork W2999589555 @default.
- W3014010584 hasRelatedWork W3137189469 @default.
- W3014010584 hasRelatedWork W4235530921 @default.
- W3014010584 hasRelatedWork W4243252198 @default.
- W3014010584 isParatext "false" @default.
- W3014010584 isRetracted "false" @default.
- W3014010584 magId "3014010584" @default.
- W3014010584 workType "article" @default.