Collaborator Effort Optimisation in Multimodal Crowdsourcing for Transcribing Historical Manuscripts

Granell, Emilio; Martínez-Hinarejos, Carlos D.

doi:10.1007/978-3-319-49169-1_23

Cited by 1 publication

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar statistically significant improvements can be achieved, optimizing the effort of the collaborators. In this test set, the optimal batch size B is 30 lines . In Table and Figure , it can be observed that optimizing the collaborator effort produces 30.0%±4.1 of WER after the sixth collaborator.…”

Section: Resultsmentioning

confidence: 96%

“…In this test set, the optimal batch size B is 30 lines. 28 In Table 2 and Figure 6, it can be observed that optimizing the collaborator effort produces 30.0% ± 4.1 of WER after the sixth collaborator. Besides, with this effort optimization, the obtained improvements are statistically significant after the collaboration of the fourth collaborator.…”

Section: Post-edition Crowdsourcing Experimentsmentioning

confidence: 91%

“…These results were presented in previous works. 10,28 As can be observed, the overall post-edition best result is obtained when all people collaborate with full effort, ie, giving the speech dictation of the whole set of text lines. In this case, the .…”

Section: Post-edition Crowdsourcing Experimentsmentioning

confidence: 96%

“…The initial multimodal crowdsourcing framework allowed us to use speech utterances for improving the transcription of historical manuscripts. This system was improved by adding a line selection module that allows us to optimize the collaboration effort (CE) . Then, it was tested in a real scenario where the speech collaborations were acquired from mobile devices …”

Section: Related Workmentioning

confidence: 99%

“…This system was improved by adding a line selection module that allows us to optimize the collaboration effort (CE). 28 Then, it was tested in a real scenario where the speech collaborations were acquired from mobile devices. 7 In this work, the data fusion and lattice transformation performed by this crowdsourcing framework is studied.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Multimodality, interactivity, and crowdsourcing for document transcription

Granell

Romero

Martínez-Hinarejos

2018

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Knowledge mining from documents usually use document engineering techniques that allow the user to access the information contained in documents of interest. In this framework, transcription may provide efficient access to the contents of handwritten documents. Manual transcription is a time‐consuming task that can be sped up by using different mechanisms. A first possibility is employing state‐of‐the‐art handwritten text recognition systems to obtain an initial draft transcription that can be manually amended. A second option is employing crowdsourcing to obtain a massive but not error‐free draft transcription. In this case, when collaborators employ mobile devices, speech dictation can be used as a transcription source, and speech and handwritten text recognition can be fused to provide a better draft transcription, which can be amended with even less effort. A final option is using interactive assistive frameworks, where the automatic system that provides the draft transcription and the transcriber cooperate to generate the final transcription. The novel contributions presented in this work include the study of the data fusion on a multimodal crowdsourcing framework and its integration with an interactive system. The use of the proposed solutions reduces the required transcription effort and optimizes the overall performance and usability, allowing for a better transcription process.

show abstract

Section: Resultsmentioning

confidence: 96%

Section: Post-edition Crowdsourcing Experimentsmentioning

confidence: 91%

Section: Post-edition Crowdsourcing Experimentsmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations