Measuring the performance of a location-aware text prediction system
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/20.500.12207/4456 |
Resumo: | In recent years, some works have discussed the conception of location-aware Augmentative and Alternative Communication (AAC) systems with very positive feedback from participants. However, in most cases, complementary quantitative evaluations have not been carried out to confirm those results. To contribute to clarifying the validity of these approaches, our study quantitatively evaluated the effect of using language models with location knowledge on the efficiency of a word and sentence prediction system. Using corpora collected for three different locations (classroom, school cafeteria, home), location-specific language models were trained with sentences from each location and compared with a traditional all-purpose language model, trained on all corpora. User tests showed a modest mean improvement of 2.4% and 1.3% for Words Per Minute (WPM) and Keystroke Saving Rate (KSR), respectively, but the differences were not statistically significant. Since our text prediction system relies on the concept of sentence reuse, we ran a set of simulations with language models having different sentence knowledge levels (0%, 25%, 50%, 75%, 100%). We also introduced in the comparison a second location-aware strategy that combines the location-specific approach with the all-purpose approach (mixed approach). The mixed language models performed better under low sentence-reuse conditions (0%, 25%, 50%) with 1.0%, 1.3%, and 1.2% KSR improvements, respectively. The location-specific language models performed better under high sentence-reuse conditions (75%, 100%) with 1.7% and 1.5% KSR improvements, respectively. |
id |
RCAP_68e0e2cb0d8a1e999304d11fbdba67ad |
---|---|
oai_identifier_str |
oai:repositorio.ipbeja.pt:20.500.12207/4456 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
|
spelling |
Measuring the performance of a location-aware text prediction systemAugmentative and alternative communicationCommunication rateLocation-awarenessSentence predictionWord predictionIn recent years, some works have discussed the conception of location-aware Augmentative and Alternative Communication (AAC) systems with very positive feedback from participants. However, in most cases, complementary quantitative evaluations have not been carried out to confirm those results. To contribute to clarifying the validity of these approaches, our study quantitatively evaluated the effect of using language models with location knowledge on the efficiency of a word and sentence prediction system. Using corpora collected for three different locations (classroom, school cafeteria, home), location-specific language models were trained with sentences from each location and compared with a traditional all-purpose language model, trained on all corpora. User tests showed a modest mean improvement of 2.4% and 1.3% for Words Per Minute (WPM) and Keystroke Saving Rate (KSR), respectively, but the differences were not statistically significant. Since our text prediction system relies on the concept of sentence reuse, we ran a set of simulations with language models having different sentence knowledge levels (0%, 25%, 50%, 75%, 100%). We also introduced in the comparison a second location-aware strategy that combines the location-specific approach with the all-purpose approach (mixed approach). The mixed language models performed better under low sentence-reuse conditions (0%, 25%, 50%) with 1.0%, 1.3%, and 1.2% KSR improvements, respectively. The location-specific language models performed better under high sentence-reuse conditions (75%, 100%) with 1.7% and 1.5% KSR improvements, respectively.ACM Digital Library2015-07-08T09:50:52Z2015-07-03T00:00:00Z2015-06-01T00:00:00Z2015-06-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/20.500.12207/4456eng1936-7228metadata only accessinfo:eu-repo/semantics/openAccessGarcia, LuísOliveira, LuísMatos, Davidreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2022-06-23T07:46:51ZPortal AgregadorONG |
dc.title.none.fl_str_mv |
Measuring the performance of a location-aware text prediction system |
title |
Measuring the performance of a location-aware text prediction system |
spellingShingle |
Measuring the performance of a location-aware text prediction system Garcia, Luís Augmentative and alternative communication Communication rate Location-awareness Sentence prediction Word prediction |
title_short |
Measuring the performance of a location-aware text prediction system |
title_full |
Measuring the performance of a location-aware text prediction system |
title_fullStr |
Measuring the performance of a location-aware text prediction system |
title_full_unstemmed |
Measuring the performance of a location-aware text prediction system |
title_sort |
Measuring the performance of a location-aware text prediction system |
author |
Garcia, Luís |
author_facet |
Garcia, Luís Oliveira, Luís Matos, David |
author_role |
author |
author2 |
Oliveira, Luís Matos, David |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Garcia, Luís Oliveira, Luís Matos, David |
dc.subject.por.fl_str_mv |
Augmentative and alternative communication Communication rate Location-awareness Sentence prediction Word prediction |
topic |
Augmentative and alternative communication Communication rate Location-awareness Sentence prediction Word prediction |
description |
In recent years, some works have discussed the conception of location-aware Augmentative and Alternative Communication (AAC) systems with very positive feedback from participants. However, in most cases, complementary quantitative evaluations have not been carried out to confirm those results. To contribute to clarifying the validity of these approaches, our study quantitatively evaluated the effect of using language models with location knowledge on the efficiency of a word and sentence prediction system. Using corpora collected for three different locations (classroom, school cafeteria, home), location-specific language models were trained with sentences from each location and compared with a traditional all-purpose language model, trained on all corpora. User tests showed a modest mean improvement of 2.4% and 1.3% for Words Per Minute (WPM) and Keystroke Saving Rate (KSR), respectively, but the differences were not statistically significant. Since our text prediction system relies on the concept of sentence reuse, we ran a set of simulations with language models having different sentence knowledge levels (0%, 25%, 50%, 75%, 100%). We also introduced in the comparison a second location-aware strategy that combines the location-specific approach with the all-purpose approach (mixed approach). The mixed language models performed better under low sentence-reuse conditions (0%, 25%, 50%) with 1.0%, 1.3%, and 1.2% KSR improvements, respectively. The location-specific language models performed better under high sentence-reuse conditions (75%, 100%) with 1.7% and 1.5% KSR improvements, respectively. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-07-08T09:50:52Z 2015-07-03T00:00:00Z 2015-06-01T00:00:00Z 2015-06-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/20.500.12207/4456 |
url |
http://hdl.handle.net/20.500.12207/4456 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1936-7228 |
dc.rights.driver.fl_str_mv |
metadata only access info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
metadata only access |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
ACM Digital Library |
publisher.none.fl_str_mv |
ACM Digital Library |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
|
repository.mail.fl_str_mv |
|
_version_ |
1777301162407493632 |