A Probabilistic Approach to Pronunciation by Analogy

The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kujala, Janne V, Keurulainen, Aleksi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Kujala, Janne V
Keurulainen, Aleksi
description The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the best published word accuracy of 65.5% (for the 20,000 word NETtalk corpus) suggests there is much room for improvement in it. Previous PbA algorithms have used several different scoring strategies such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy (66.21% for the NETtalk corpus) than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance climbs up to 66.6%, and further improvements are possible by combining this method with other methods.
doi_str_mv 10.48550/arxiv.1109.4531
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1109_4531</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1109_4531</sourcerecordid><originalsourceid>FETCH-LOGICAL-a651-b74146a9f965e46e56a8e1c3cb589d9b24d6666263daad32757fab9fe70b1db43</originalsourceid><addsrcrecordid>eNotzr1ugzAUBWAvHSLaPVPkF4Bi_AMeEWqbSpGagR3da5vEEsHI0Kq8fUvas5zhSEcfIXuWZ6KSMn-G-O2_MsZynQnJ2Y6Imp5jQEA_-HnxhtbTFAOYK13Ctoyfo_Gw-DBSXGk9whAu6yN56GGY3dN_J6R9fWmbY3r6eHtv6lMKSrIUS8GEAt1rJZ1QTiqoHDPcoKy01VgIq35TKG4BLC9KWfaAundljsyi4Ak5_N3e1d0U_Q3i2m36btPzH9HpPvQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Probabilistic Approach to Pronunciation by Analogy</title><source>arXiv.org</source><creator>Kujala, Janne V ; Keurulainen, Aleksi</creator><creatorcontrib>Kujala, Janne V ; Keurulainen, Aleksi</creatorcontrib><description>The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the best published word accuracy of 65.5% (for the 20,000 word NETtalk corpus) suggests there is much room for improvement in it. Previous PbA algorithms have used several different scoring strategies such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy (66.21% for the NETtalk corpus) than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance climbs up to 66.6%, and further improvements are possible by combining this method with other methods.</description><identifier>DOI: 10.48550/arxiv.1109.4531</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2011-09</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1109.4531$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1109.4531$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kujala, Janne V</creatorcontrib><creatorcontrib>Keurulainen, Aleksi</creatorcontrib><title>A Probabilistic Approach to Pronunciation by Analogy</title><description>The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the best published word accuracy of 65.5% (for the 20,000 word NETtalk corpus) suggests there is much room for improvement in it. Previous PbA algorithms have used several different scoring strategies such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy (66.21% for the NETtalk corpus) than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance climbs up to 66.6%, and further improvements are possible by combining this method with other methods.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzr1ugzAUBWAvHSLaPVPkF4Bi_AMeEWqbSpGagR3da5vEEsHI0Kq8fUvas5zhSEcfIXuWZ6KSMn-G-O2_MsZynQnJ2Y6Imp5jQEA_-HnxhtbTFAOYK13Ctoyfo_Gw-DBSXGk9whAu6yN56GGY3dN_J6R9fWmbY3r6eHtv6lMKSrIUS8GEAt1rJZ1QTiqoHDPcoKy01VgIq35TKG4BLC9KWfaAundljsyi4Ak5_N3e1d0U_Q3i2m36btPzH9HpPvQ</recordid><startdate>20110921</startdate><enddate>20110921</enddate><creator>Kujala, Janne V</creator><creator>Keurulainen, Aleksi</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20110921</creationdate><title>A Probabilistic Approach to Pronunciation by Analogy</title><author>Kujala, Janne V ; Keurulainen, Aleksi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a651-b74146a9f965e46e56a8e1c3cb589d9b24d6666263daad32757fab9fe70b1db43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Kujala, Janne V</creatorcontrib><creatorcontrib>Keurulainen, Aleksi</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kujala, Janne V</au><au>Keurulainen, Aleksi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Probabilistic Approach to Pronunciation by Analogy</atitle><date>2011-09-21</date><risdate>2011</risdate><abstract>The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by analogy (PbA) is a data-driven method of constructing pronunciations for novel words from concatenated segments of known words and their pronunciations. PbA performs relatively well with English and outperforms several other proposed methods. However, the best published word accuracy of 65.5% (for the 20,000 word NETtalk corpus) suggests there is much room for improvement in it. Previous PbA algorithms have used several different scoring strategies such as the product of the frequencies of the component pronunciations of the segments, or the number of different segmentations that yield the same pronunciation, and different combinations of these methods, to evaluate the candidate pronunciations. In this article, we instead propose to use a probabilistically justified scoring rule. We show that this principled approach alone yields better accuracy (66.21% for the NETtalk corpus) than any previously published PbA algorithm. Furthermore, combined with certain ad hoc modifications motivated by earlier algorithms, the performance climbs up to 66.6%, and further improvements are possible by combining this method with other methods.</abstract><doi>10.48550/arxiv.1109.4531</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1109.4531
ispartof
issn
language eng
recordid cdi_arxiv_primary_1109_4531
source arXiv.org
subjects Computer Science - Computation and Language
title A Probabilistic Approach to Pronunciation by Analogy
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T00%3A57%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Probabilistic%20Approach%20to%20Pronunciation%20by%20Analogy&rft.au=Kujala,%20Janne%20V&rft.date=2011-09-21&rft_id=info:doi/10.48550/arxiv.1109.4531&rft_dat=%3Carxiv_GOX%3E1109_4531%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true