{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T05:55:52Z","timestamp":1674798952071},"reference-count":34,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T00:00:00Z","timestamp":1674518400000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,1,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>If one sees the place name Houston Mercer Dog Run in New York, how does one know how to pronounce it? Assuming one knows that Houston in New York is pronounced \/\u02c8ha\u028ast\u0259n\/ and not like the Texas city (\/\u02c8hju\u02d0st\u0259n\/), then one can probably guess that \/\u02c8ha\u028ast\u0259n\/ is also used in the name of the dog park. We present a novel architecture that learns to use the pronunciations of neighboring names in order to guess the pronunciation of a given target feature. Applied to Japanese place names, we demonstrate the utility of the model to finding and proposing corrections for errors in Google Maps.<\/jats:p>\n               <jats:p>To demonstrate the utility of this approach to structurally similar problems, we also report on an application to a totally different task: Cognate reflex prediction in comparative historical linguistics. A version of the code has been open-sourced.1<\/jats:p>","DOI":"10.1162\/tacl_a_00535","type":"journal-article","created":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T16:27:14Z","timestamp":1674577634000},"page":"85-101","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation"],"prefix":"10.1162","volume":"11","author":[{"given":"Llion","family":"Jones","sequence":"first","affiliation":[{"name":"Google Japan. llion@google.com"}]},{"given":"Richard","family":"Sproat","sequence":"additional","affiliation":[{"name":"Google Japan. rws@google.com"}]},{"given":"Haruko","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Google Japan. ishikawa@google.com"}]},{"given":"Alexander","family":"Gutkin","sequence":"additional","affiliation":[{"name":"Google UK. agutkin@google.com"}]}],"member":"281","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"2023012615513355400_bib1","doi-asserted-by":"publisher","first-page":"4960","DOI":"10.1109\/ICASSP.2016.7472621","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","volume-title":"Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Chan","year":"2016"},{"key":"2023012615513355400_bib2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.18653\/v1\/W17-4109","article-title":"Glyph-aware embedding of Chinese characters","volume-title":"Proceedings of the First Workshop on Subword and Character Level Models in NLP","author":"Dai","year":"2017"},{"key":"2023012615513355400_bib3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3235-1_3","volume-title":"Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses","author":"Good","year":"2000","edition":"2nd edition"},{"key":"2023012615513355400_bib4","first-page":"1349","article-title":"Improving homograph disambiguation with supervised machine learning","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","author":"Gorman","year":"2018"},{"key":"2023012615513355400_bib5","volume-title":"Introduction to Probability","author":"Grinstead","year":"1997","edition":"2nd edition"},{"issue":"4","key":"2023012615513355400_bib6","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/MPRV.2008.80","article-title":"OpenStreetMap: User-generated street maps","volume":"7","author":"Haklay","year":"2008","journal-title":"IEEE Pervasive Computing"},{"key":"2023012615513355400_bib7","volume-title":"Ekimei Gaku Ny\u016bmon (An Introduction to the Study of Station Names)","author":"Imao","year":"2020"},{"key":"2023012615513355400_bib8","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/tacl_a_00065","article-title":"Google\u2019s multilingual neural machine translation system: Enabling zero-shot translation","volume":"5","author":"Johnson","year":"2017","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2023012615513355400_bib9","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.18653\/v1\/2020.coling-main.192","article-title":"Neural text normalization leveraging similarities of strings and sounds","volume-title":"Proceedings of the 28th International Conference on Computational Linguistics","author":"Kawamura","year":"2020"},{"key":"2023012615513355400_bib10","doi-asserted-by":"publisher","first-page":"70","DOI":"10.18653\/v1\/2022.sigtyp-1.9","article-title":"Mockingbird at the SIGTYP 2022 shared task: Two types of models for the prediction of cognate reflexes","volume-title":"Proceedings of the 4th Workshop on Research in Computational Typology and Multilingual NLP (ACL SIGTYP)","author":"Kirov","year":"2022"},{"key":"2023012615513355400_bib11","first-page":"388","article-title":"Statistical significance tests for machine translation evaluation","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing","author":"Koehn","year":"2004"},{"key":"2023012615513355400_bib12","doi-asserted-by":"crossref","first-page":"52","DOI":"10.18653\/v1\/2022.sigtyp-1.7","article-title":"The SIGTYP 2022 shared task on the prediction of cognate reflexes","volume-title":"Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","author":"List","year":"2022"},{"key":"2023012615513355400_bib13","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01252-6_6","article-title":"Image inpainting for irregular holes using partial convolutions","volume-title":"Proceedings of the 15th European Conference on Computer Vision (ECCV 2018)","author":"Liu","year":"2018"},{"key":"2023012615513355400_bib14","doi-asserted-by":"publisher","first-page":"190","DOI":"10.18653\/v1\/N19-2024","article-title":"Neural text normalization with subword units","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)","author":"Mansfield","year":"2019"},{"key":"2023012615513355400_bib15","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TASLP.2019.2955246","article-title":"Hierarchical character embeddings: Learning phonological and semantic representations in languages of logographic origin using recursive neural networks","volume":"28","author":"Nguyen","year":"2020","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"2023012615513355400_bib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1057\/s41599-021-00810-0","article-title":"I know the name well, but cannot read it correctly: Difficulties in reading recent Japanese names","volume":"8","author":"Ogihara","year":"2021","journal-title":"Humanities and Social Sciences Communications"},{"key":"2023012615513355400_bib17","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.21437\/Interspeech.2020-1094","article-title":"g2pM: A neural grapheme-to-phoneme conversion package for Mandarin Chinese based on a new open benchmark dataset","volume-title":"Proceedings of Interspeech 2020","author":"Park","year":"2020"},{"key":"2023012615513355400_bib18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.18653\/v1\/W17-5403","article-title":"Massively multilingual neural grapheme-to-phoneme conversion","volume-title":"Proceedings of the First Workshop on Building Linguistically Generalizable NLP Systems","author":"Peters","year":"2017"},{"key":"2023012615513355400_bib19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.specom.2019.02.003","article-title":"Text normalization using memory augmented neural networks","volume":"109","author":"Pramanik","year":"2019","journal-title":"Speech Communication"},{"key":"2023012615513355400_bib20","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1109\/SLT.2018.8639034","article-title":"Deep context: End-to-end contextual speech recognition","volume-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)","author":"Pundak","year":"2018"},{"key":"2023012615513355400_bib21","first-page":"4225","article-title":"Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks","volume-title":"Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Rao","year":"2015"},{"key":"2023012615513355400_bib22","first-page":"167","article-title":"\u5730\u540d\u8868\u8a18\u3068JIS\u6f22\u5b57, Chimei hy\u014dki to JIS kanji, (on the expression of place names and JIS Chinese characters)","volume":"20","author":"Sat\u014d","year":"1985","journal-title":"\u6c34\u8def\u90e8\u7814\u7a76\u5831\u544a, Suirobuz Kenky\u016b H\u014dkoku, (Hydrographic Department Research Report)"},{"issue":"3","key":"2023012615513355400_bib23","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1609\/aimag.v29i3.2157","article-title":"Collective classification in network data","volume":"29","author":"Sen","year":"2008","journal-title":"AI Magazine"},{"key":"2023012615513355400_bib24","doi-asserted-by":"publisher","first-page":"4109","DOI":"10.21437\/Interspeech.2021-502","article-title":"Polyphone disambiguation in Mandarin Chinese with semi-supervised learning","volume-title":"Proceedings of Interspeech 2021","author":"Yi","year":"2021"},{"key":"2023012615513355400_bib25","doi-asserted-by":"publisher","first-page":"754","DOI":"10.21437\/Interspeech.2017-35","article-title":"An RNN model of text normalization","volume-title":"Proceedings of Interspeech","author":"Sproat","year":"2017"},{"key":"2023012615513355400_bib26","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/SLT.2016.7846248","article-title":"Jointly learning to align and convert graphemes to phonemes with neural attention models","volume-title":"2016 IEEE Spoken Language Technology Workshop (SLT)","author":"Toshniwal","year":"2016"},{"issue":"3","key":"2023012615513355400_bib27","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1080\/08839514.2020.1842108","article-title":"Neural text normalization in speech-to-text systems with rich features","volume":"35","author":"Tran","year":"2021","journal-title":"Applied Artificial Intelligence"},{"key":"2023012615513355400_bib28","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017)","author":"Vaswani","year":"2017"},{"key":"2023012615513355400_bib29","first-page":"3330","article-title":"Sequence-to-sequence neural net models for grapheme-to-phoneme conversion","volume-title":"Proceedings of Interspeech","author":"Yao","year":"2015"},{"key":"2023012615513355400_bib30","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-1-4612-1894-4_12","article-title":"Homograph disambiguation in text-to-speech synthesis","volume-title":"Progress in Speech Synthesis","author":"Yarowsky","year":"1996"},{"issue":"6","key":"2023012615513355400_bib31","doi-asserted-by":"publisher","DOI":"10.3390\/app9061143","article-title":"Grapheme-to-phoneme conversion with convolutional neural networks","volume":"9","author":"Yolchuyeva","year":"2019","journal-title":"Applied Sciences"},{"key":"2023012615513355400_bib32","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/s10772-018-9521-x","article-title":"Text normalization with convolutional neural networks","volume":"21","author":"Yolchuyeva","year":"2018","journal-title":"International Journal of Speech Technology"},{"key":"2023012615513355400_bib33","first-page":"8234","article-title":"Multilingual grapheme-to-phoneme conversion with byte representatoin","volume-title":"Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Mingzhi","year":"2020"},{"issue":"2","key":"2023012615513355400_bib34","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1162\/coli_a_00349","article-title":"Neural models of text normalization for speech applications","volume":"45","author":"Zhang","year":"2019","journal-title":"Computational Linguistics"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00535\/2068127\/tacl_a_00535.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00535\/2068127\/tacl_a_00535.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T15:52:24Z","timestamp":1674748344000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00535\/114597\/Helpful-Neighbors-Leveraging-Neighbors-in"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00535","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}