Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen, F. Beaufays, Tom Y. Ouyang, M. Riley, David Rybach
{"title":"通过加权有限状态传感器的音译移动键盘输入","authors":"Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen, F. Beaufays, Tom Y. Ouyang, M. Riley, David Rybach","doi":"10.18653/v1/W17-4002","DOIUrl":null,"url":null,"abstract":"We present an extension to a mobile key-board input decoder based on finite-state transducers that provides general translit-eration support, and demonstrate its use for input of South Asian languages using a QWERTY keyboard. On-device keyboard decoders must operate under strict latency and memory constraints, and we present several transducer optimizations that allow for high accuracy decoding under such constraints. Our methods yield substantial accuracy improvements and latency reductions over an existing baseline translit-eration keyboard approach. The resulting system was launched for 22 languages in Google Gboard in the first half of 2017.","PeriodicalId":286427,"journal":{"name":"Finite-State Methods and Natural Language Processing","volume":"169 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"23","resultStr":"{\"title\":\"Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers\",\"authors\":\"Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen, F. Beaufays, Tom Y. Ouyang, M. Riley, David Rybach\",\"doi\":\"10.18653/v1/W17-4002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present an extension to a mobile key-board input decoder based on finite-state transducers that provides general translit-eration support, and demonstrate its use for input of South Asian languages using a QWERTY keyboard. On-device keyboard decoders must operate under strict latency and memory constraints, and we present several transducer optimizations that allow for high accuracy decoding under such constraints. Our methods yield substantial accuracy improvements and latency reductions over an existing baseline translit-eration keyboard approach. The resulting system was launched for 22 languages in Google Gboard in the first half of 2017.\",\"PeriodicalId\":286427,\"journal\":{\"name\":\"Finite-State Methods and Natural Language Processing\",\"volume\":\"169 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"23\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Finite-State Methods and Natural Language Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/W17-4002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Finite-State Methods and Natural Language Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/W17-4002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers
We present an extension to a mobile key-board input decoder based on finite-state transducers that provides general translit-eration support, and demonstrate its use for input of South Asian languages using a QWERTY keyboard. On-device keyboard decoders must operate under strict latency and memory constraints, and we present several transducer optimizations that allow for high accuracy decoding under such constraints. Our methods yield substantial accuracy improvements and latency reductions over an existing baseline translit-eration keyboard approach. The resulting system was launched for 22 languages in Google Gboard in the first half of 2017.