Matches in SemOpenAlex for { <https://semopenalex.org/work/W2921558328> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2921558328 abstract "Text normalization is a ubiquitous process that appears as the first step of many Natural Language Processing problems. However, previous Deep Learning approaches have suffered from so-called silly errors, which are undetectable on unsupervised frameworks, making those models unsuitable for deployment. In this work, we make use of an attention-based encoder-decoder architecture that overcomes these undetectable errors by using a fine-grained character-level approach rather than a word-level one. Furthermore, our new general-purpose encoder based on causal convolutions, called Causal Feature Extractor (CFE), is introduced and compared to other common encoders. The experimental results show the feasibility of this encoder, which leverages the attention mechanisms the most and obtains better results in terms of accuracy, number of parameters and convergence time. While our method results in a slightly worse initial accuracy (92.74%), errors can be automatically detected and, thus, more readily solved, obtaining a more robust model for deployment. Furthermore, there is still plenty of room for future improvements that will push even further these advantages." @default.
- W2921558328 created "2019-03-22" @default.
- W2921558328 creator A5064617496 @default.
- W2921558328 creator A5089424793 @default.
- W2921558328 date "2019-03-06" @default.
- W2921558328 modified "2023-09-23" @default.
- W2921558328 title "A Character-Level Approach to the Text Normalization Problem Based on a New Causal Encoder." @default.
- W2921558328 cites W2164280277 @default.
- W2921558328 cites W2171421863 @default.
- W2921558328 cites W2531207078 @default.
- W2921558328 cites W2546744831 @default.
- W2921558328 cites W2737886250 @default.
- W2921558328 cites W2963251942 @default.
- W2921558328 cites W2964308564 @default.
- W2921558328 hasPublicationYear "2019" @default.
- W2921558328 type Work @default.
- W2921558328 sameAs 2921558328 @default.
- W2921558328 citedByCount "1" @default.
- W2921558328 countsByYear W29215583282020 @default.
- W2921558328 crossrefType "posted-content" @default.
- W2921558328 hasAuthorship W2921558328A5064617496 @default.
- W2921558328 hasAuthorship W2921558328A5089424793 @default.
- W2921558328 hasConcept C105339364 @default.
- W2921558328 hasConcept C108583219 @default.
- W2921558328 hasConcept C111919701 @default.
- W2921558328 hasConcept C11413529 @default.
- W2921558328 hasConcept C118505674 @default.
- W2921558328 hasConcept C136886441 @default.
- W2921558328 hasConcept C144024400 @default.
- W2921558328 hasConcept C154945302 @default.
- W2921558328 hasConcept C19165224 @default.
- W2921558328 hasConcept C199360897 @default.
- W2921558328 hasConcept C204321447 @default.
- W2921558328 hasConcept C2524010 @default.
- W2921558328 hasConcept C2780861071 @default.
- W2921558328 hasConcept C33923547 @default.
- W2921558328 hasConcept C41008148 @default.
- W2921558328 hasConcept C98045186 @default.
- W2921558328 hasConceptScore W2921558328C105339364 @default.
- W2921558328 hasConceptScore W2921558328C108583219 @default.
- W2921558328 hasConceptScore W2921558328C111919701 @default.
- W2921558328 hasConceptScore W2921558328C11413529 @default.
- W2921558328 hasConceptScore W2921558328C118505674 @default.
- W2921558328 hasConceptScore W2921558328C136886441 @default.
- W2921558328 hasConceptScore W2921558328C144024400 @default.
- W2921558328 hasConceptScore W2921558328C154945302 @default.
- W2921558328 hasConceptScore W2921558328C19165224 @default.
- W2921558328 hasConceptScore W2921558328C199360897 @default.
- W2921558328 hasConceptScore W2921558328C204321447 @default.
- W2921558328 hasConceptScore W2921558328C2524010 @default.
- W2921558328 hasConceptScore W2921558328C2780861071 @default.
- W2921558328 hasConceptScore W2921558328C33923547 @default.
- W2921558328 hasConceptScore W2921558328C41008148 @default.
- W2921558328 hasConceptScore W2921558328C98045186 @default.
- W2921558328 hasOpenAccess W2921558328 @default.
- W2921558328 hasRelatedWork W1845607459 @default.
- W2921558328 hasRelatedWork W1990884907 @default.
- W2921558328 hasRelatedWork W2157800108 @default.
- W2921558328 hasRelatedWork W2176796957 @default.
- W2921558328 hasRelatedWork W2182277027 @default.
- W2921558328 hasRelatedWork W2395390206 @default.
- W2921558328 hasRelatedWork W2546744831 @default.
- W2921558328 hasRelatedWork W2574219039 @default.
- W2921558328 hasRelatedWork W2962939608 @default.
- W2921558328 hasRelatedWork W3020242586 @default.
- W2921558328 hasRelatedWork W3045733172 @default.
- W2921558328 hasRelatedWork W3046330735 @default.
- W2921558328 hasRelatedWork W3126524535 @default.
- W2921558328 hasRelatedWork W3141945023 @default.
- W2921558328 hasRelatedWork W3171589712 @default.
- W2921558328 hasRelatedWork W3194203264 @default.
- W2921558328 hasRelatedWork W3195633477 @default.
- W2921558328 hasRelatedWork W3200918848 @default.
- W2921558328 hasRelatedWork W3206275068 @default.
- W2921558328 hasRelatedWork W2185473723 @default.
- W2921558328 isParatext "false" @default.
- W2921558328 isRetracted "false" @default.
- W2921558328 magId "2921558328" @default.
- W2921558328 workType "article" @default.