Kernowek and English

Resources for machine translation between Kernowek and English

Corpus:

External resources

• Language pair repository: https://github.swarthmore.edu/Ling073-sp26/ling073-cor-eng

• English transducer repository:

Cor to ENG Evaluation

#	Original (Kernowek)	English Translation	biltrans output	ML output
1	An Radyo yw towlen unn our seythenyek neb a sen ilow Kernow ha Keltek, ha presentys yn Kernewek.	‘An Radyo is a weekly one hour radio show playing Cornish and Celtic music, presented in Cornish. ’	^*An/*An$ ^Radyo<n><m><sg><m_soft>/Radio<n><m><m><sg><m_soft>$ ^*yw/*yw$ ^towlen<n><f><sg><m_rad>/Programme<n><f><f><sg><m_rad>$ ^*unn/*unn$ ^eur<n><m><sg><m_soft>/Hour<n><f><m><sg><m_soft>/Hour<n><m><m><sg><m_soft>$ ^*seythenyek/*seythenyek$ ^*neb/*neb$ ^*a/*a$ ^*sen/*sen$ ^ilow<n><f><pl><m_soft>/Music<n><f><f><pl><m_soft>$ ^*Kernow/*Kernow$ ^*ha/*ha$ ^*Keltek/*Keltek$^,<cm>/,<cm>$ ^*ha/*ha$ ^*presentys/*presentys$ ^*yn/*yn$ ^*Kernewek/*Kernewek$^.<sent>/.<sent>$	*An #Radio *yw #Programme *unn #Hour *seythenyek *neb *a *sen #Music *Kernow *ha *Keltek, *ha *presentys *yn *Kernewek.
2	Yma nowodhow yn Kernewek ynwedh ha keswel traweythyek.	‘We also have news in Cornish and sometimes an interview. ’	^*Yma/*Yma$ ^nowodhow<n><m><pl><m_soft>/News<n><m><m><pl><m_soft>$ ^*yn/*yn$ ^*Kernewek/*Kernewek$ ^*ynwedh/*ynwedh$ ^*ha/*ha$ ^keswel<n><m><sg><m_rad>/Interview<n><m><m><sg><m_rad>$ ^*traweythyek/*traweythyek$^.<sent>/.<sent>$	*Yma #News *yn *Kernewek *ynwedh *ha #Interview *traweythyek.
3	Y hyllir agan klewes der Coast FM, Source FM, Chaos Radio ha Liskeard & Looe Radio.	'You can also hear the show on Coast FM, Source FM, Chaos Radio and Liskeard & Looe Radio. '	^*Y/*Y$ ^*hyllir/*hyllir$ ^*agan/*agan$ ^*klewes/*klewes$ ^*der/*der$ ^*Coast/*Coast$ ^*FM/*FM$^,<cm>/,<cm>$ ^*Source/*Source$ ^*FM/*FM$^,<cm>/,<cm>$ ^*Chaos/*Chaos$ ^*Radio/*Radio$ ^*ha/*ha$ ^*Liskeard/*Liskeard$ & ^*Looe/*Looe$ ^*Radio/*Radio$^.<sent>/.<sent>$	*Y *hyllir *agan *klewes *der *Coast *FM, *Source *FM, *Chaos *Radio *ha *Liskeard & *Looe *Radio.
4	Taves byw yw Kernewek, ha ni a wra ynnia orth agan studhyoryon dhe usya an asnodhow kavadow rag gwellhe aga yeth. Ottomma nebes tybyansow:	'Cornish, Kernewek, is a living language and we encourage all our students to use the many resources available to improve their language. Here are some ideas:’	^Taves<n><m><sg><m_rad>/Language<n><m><m><sg><m_rad>$ ^*byw/*byw$ ^*yw/*yw$ ^*Kernewek/*Kernewek$^,<cm>/,<cm>$ ^*ha/*ha$ ^*ni/*ni$ ^*a/*a$ ^*wra/*wra$ ^*ynnia/*ynnia$ ^*orth/*orth$ ^*agan/*agan$ ^studhyer<n><m><pl><m_soft>/Student<n><m><m><pl><m_soft>$ ^*dhe/*dhe$ ^*usya/*usya$ ^*an/*an$ ^asnodhow<n><m><pl><m_soft>/Resources<n><m><m><pl><m_soft>$ ^*kavadow/*kavadow$ ^*rag/*rag$ ^*gwellhe/*gwellhe$ ^*aga/*aga$ ^yeth<n><f><sg><m_soft>/Language<n><f><f><sg><m_soft>$^.<sent>/.<sent>$ ^*Ottomma/*Ottomma$ ^nebes<n><m><sg><m_soft>/Some<n><m><m><sg><m_soft>$ ^tybyans<n><m><pl><m_rad>/Idea<n><m><m><pl><m_rad>/Opinion<n><m><m><pl><m_rad>/Thought<n><m><m><pl><m_rad>$^:<sent>/:<sent>$	#Language *byw *yw *Kernewek, *ha *ni *a *wra *ynnia *orth *agan #Student *dhe *usya *an #Resources *kavadow *rag *gwellhe *aga #Language. *Ottomma #Some #Idea:
5	Yma bagas lyverfas nowydh KDL omma.	'There is a new 'KDL' Facebook group here.’	^*Yma/*Yma$ ^bagas<n><m><sg><m_rad>/Group<n><m><m><sg><m_rad>$ ^*lyverfas/*lyverfas$ ^*nowydh/*nowydh$ ^*KDL/*KDL$ ^*omma/*omma$^.<sent>/.<sent>$	*Yma #Group *lyverfas *nowydh *KDL *omma.
6	Penn-seythen Kernewek yw chons meur a wellhe dha Gernewek kewsys.	'The annual Cornish Language Weekend is a great opportunity to improve your spoken Cornish.’	^Penn-seythen<n><m><sg><m_rad>/Weekend<n><m><m><sg><m_rad>$ ^*Kernewek/*Kernewek$ ^*yw/*yw$ ^chons<n><m><sg><m_asp>/Chance<n><m><m><sg><m_asp>/Opportunity<n><m><m><sg><m_asp>$ ^*meur/*meur$ ^*a/*a$ ^*wellhe/*wellhe$ ^*dha/*dha$ ^*Gernewek/*Gernewek$ ^*kewsys/*kewsys$^.<sent>/.<sent>$	#Weekend *Kernewek *yw #Chance *meur *a *wellhe *dha *Gernewek *kewsys.
7	Y tal dhe bub studhyor kemeres rann mars yw possybyl.	'All students should try it if they can.’	^*Y/*Y$ ^*tal/*tal$ ^*dhe/*dhe$ ^*bub/*bub$ ^*studhyor/*studhyor$ ^*kemeres/*kemeres$ ^*rann/*rann$ ^*mars/*mars$ ^*yw/*yw$ ^*possybyl/*possybyl$^.<sent>/.<sent>$	*Y *tal *dhe *bub *studhyor *kemeres *rann *mars *yw *possybyl.
8	Goslowes orth An Nowodhow, bollyn pymp-mynysen orth BBC Radyo Kernow a-dro dhe 3.55 p.m. pub dy' Sul.	‘Listen to An Nowodhow, a five minute news bulletin from BBC Radio Cornwall about 3.55 p.m. every Sunday.’	^*Goslowes/*Goslowes$ ^*orth/*orth$ ^*An/*An$ ^Nowodhow<n><m><pl><m_soft>/News<n><m><m><pl><m_soft>$^,<cm>/,<cm>$ ^*bollyn/*bollyn$ ^*pymp/*pymp$-^*mynysen/*mynysen$ ^*orth/*orth$ ^*BBC/*BBC$ ^Radyo<n><m><sg><m_soft>/Radio<n><m><m><sg><m_soft>$ ^*Kernow/*Kernow$ ^*a/*a$-^*dro/*dro$ ^*dhe/*dhe$ ^*3/*3$^.<sent>/.<sent>$^*55/*55$ ^*p/*p$^.<sent>/.<sent>$^*m/*m$^.<sent>/.<sent>$ ^*pub/*pub$ ^*dy/*dy$' ^*Sul/*Sul$^.<sent>/.<sent>$	*Goslowes *orth *An #News, *bollyn *pymp-*mynysen *orth *BBC #Radio *Kernow *a-*dro *dhe *3.*55 *p.*m. *pub *dy' *Sul.
9	Yma’n skrifow omma.	'The scripts are here.'	^*Yma/*Yma$’^*n/*n$ ^*skrifow/*skrifow$ ^*omma/*omma$^.<sent>/.<sent>$	*Yma’*n *skrifow *omma.
10	Ty a yll ‘goslowes arta’ ynwedh war BBC Sounds.	‘You can also listen again on BBC Sounds.’	^*Ty/*Ty$ ^*a/*a$ ^*yll/*yll$ ‘^*goslowes/*goslowes$ ^*arta/*arta$’ ^*ynwedh/*ynwedh$ ^*war/*war$ ^*BBC/*BBC$ ^*Sounds/*Sounds$^.<sent>/.<sent>$	*Ty *a *yll ‘*goslowes *arta’ *ynwedh *war *BBC *Sounds.

TOP UNKNOWN WORDS:

    14 ^an/*an$
    14 ^a/*a$
    12 ^ha/*ha$
     9 ^yn/*yn$
     9 ^dhe/*dhe$
     8 ^Kernewek/*Kernewek$
     6 ^orth/*orth$
     6 ^efanvos/*efanvos$
     5 ^yw/*yw$
     4 ^war/*war$
     4 ^termyn/*termyn$
     4 ^rag/*rag$
     4 ^n/*n$
     4 ^An/*An$
     3 ^pyth/*pyth$
     3 ^pub/*pub$
     3 ^lyver/*lyver$
     3 ^gans/*gans$
     3 ^Yma/*Yma$
     3 ^Redya/*Redya$

coverage: 77 / 414 (~0.18599033816425120773) remaining unknown forms: 337 ambiguity: 498 / 414 (~1.20289855072463768116) cor.sentences.txt Tue Apr 14 11:33:43 AM EDT 2026 77/414 ~0.18599033816425120773 \| 498/414 ~1.20289855072463768116