Monthly Archives: January 2017

Semantic disambiguation of French ‘défense’

Semantical disambiguation is lurking: défense = difesa/sanna = defense/tusk It should read: L’avvucatu priparava a so difesa. A sanna di u cignale era tronca. A tazzina era sculpita in una sanna d’elefante.

Posted in blog | Tagged , , | Comments Off on Semantic disambiguation of French ‘défense’

False positives

  There are sometimes false positives. Some words should remain untranslated, notably proper names. Interestingly, it is due to the fact that the english word ‘transport’ is the same in french: transport (fr) = transport (en) = trasportu (co).

Posted in blog | Tagged , | Comments Off on False positives

Proper noun elision

Testing #machine translation now facing new elision problem: Riventosa (fr) = A Riventosa(co) proper noun (fr) = definite article + proper noun (co) it should read: in u paese di A Riventosa (without elision) Elision rules are not trivial: le … Continue reading

Posted in blog | Comments Off on Proper noun elision

Adjective accordance

Rule-based translation : adjective accordance : interesting stuff: sur les réseaux japonais et américain (fr) = annantu à e rete sgiappunesa è americana (co) = on the japanese and american networks (en) noun (networks) is plural but adjectives (japanese and american) are … Continue reading

Posted in blog | Comments Off on Adjective accordance

Gender reversal

Now handling gender reversal: – mer (FR, feminine) = sea (EN) = mare (CO, masculine) – saveur (FR, feminine) = flavor (EN) = sapore (CO, masculine) – liqueur (FR, feminine) = liquor (EN) = licore (CO, masculine) ‘c’est une bonne liqueur’ … Continue reading

Posted in blog | Comments Off on Gender reversal

Verbal locutions

Introducing new feature for #MachineTranslation: some verbal locutions: prendre d’assaut = assaltà mettre à sac = sacchighjà prendre au collet = incappià

Posted in blog | Comments Off on Verbal locutions

Semantic disambiguation

Now considering the issue of Semantical disambiguation. Some instances For French to Corsican are: – ‘défense’ = sanna/difesa = tusk/defense – ‘vol’ = bulu/furtu = flight/theft – ‘comprend’ = capisce/cumprende = understands/comprises – ‘palais’ = palatu/palazzu = palate/palace – ‘expérience’ = … Continue reading

Posted in blog | Comments Off on Semantic disambiguation

November 26, 2016: Now scoring 95.52%

Now scoring 1 – 6/134 = 95.52%. Lack of vocabulary ‘passacaile’. It should read: ‘versu u 1678‘, ‘di a so epica‘, ‘di u so tempu‘.

Posted in blog | Comments Off on November 26, 2016: Now scoring 95.52%

Threefold ambiguity: French ‘nouvelle’

Let us mention the issue of threefold ambiguity: french ‘nouvelle’ can translate into: ‘nutizia‘ (‘piece of news’) or ‘nuvella‘ (short story’) or ‘nova‘ (‘new’) The disambiguation between ‘nutizia‘ (‘piece of news’) or ‘nuvella‘ (short story’) is semantic (hard) while the … Continue reading

Posted in blog | Comments Off on Threefold ambiguity: French ‘nouvelle’

Further reflections on the definition of ‘above human level’ translation

Some further reflections on the definition of ‘above human level’ translation: – the answer may not be based solely on the quantitative side, being of the type: ‘above 96%’, “above 97%’, ‘above 98%’, etc. – it seems the answer should also … Continue reading

Posted in blog | Comments Off on Further reflections on the definition of ‘above human level’ translation

Defining an instance of Feigenbaum test

Defining an instance of Feigenbaum test (from wikipedia: generally defined as a variant of the Turing test where a computer software attemps to imitate a human expert in a given field): Translating French into Corsican. We expect 98% accuracy and lack of gross errors in order … Continue reading

Posted in blog | Comments Off on Defining an instance of Feigenbaum test

Partitive article

Scoring 1-10/159 = 93.71%. Partitive article successfully handled: ‘participe à de nombreuses batailles’ = participeghja à numerose battaglie ‘fournit des renseignements’ = furnisce i rinsignamenti

Posted in blog | Comments Off on Partitive article

December 31, 2016: scoring 96%

scoring 1- 4/100 = 96%. It should read: natu …in Yffiniac 216 vittorie frà e quale 144 … eccituatu i criterium

Posted in blog | Comments Off on December 31, 2016: scoring 96%

January 6, 2017: scoring 96.57%

scoring 1 – 5/146 = 96.57% lack of vocabulary: ‘equine’, ‘tracter’, verdine’

Posted in blog | Comments Off on January 6, 2017: scoring 96.57%

January 8, 2017: Scoring 97.47%

Scoring 1 – 3/119 = 97.47% 2 100% consecutive sentences 1 accordance error: sviluppata should read ‘sviluppatu‘, according with ghjocu (game) and not with avventura (adventure)

Posted in blog | Comments Off on January 8, 2017: Scoring 97.47%

Scoring 97.47%: would it qualify as a successful Feigenbaum test? No.

scoring 1 – 3/119 = 97.47%: would it qualify as a successful Feigenbaum test? The answer is clearly ‘no’, since 2 errors can be identified as gross errors, i.e.some errors that a human would not do: – ‘sviluppata‘ should read ‘sviluppatu‘, … Continue reading

Posted in blog | Comments Off on Scoring 97.47%: would it qualify as a successful Feigenbaum test? No.

French ‘vis’ is multi-ambiguous

In the style of ‘I saw wood with a saw’, from French to Corsican: French ‘vis’ is multi-ambiguous: – ‘vis’ (noun singular) = vita = screw – ‘vis’ (noun plural) = vite = screws – ‘vis’ (present 1rst person) = … Continue reading

Posted in blog | Comments Off on French ‘vis’ is multi-ambiguous

Scoring 92.6%: Disambiguation engine needs to be entirely re-written

Scoring 1- 11/149 = 92.6%. Errors (9/11) come mainly from disambiguation: Disambiguation engine needs to be entirely re-written. An average 2-3% increase in accuracy is expected.

Posted in blog | Comments Off on Scoring 92.6%: Disambiguation engine needs to be entirely re-written

Semantic disambiguation of ‘palais’

Testing the #semanticdisambiguation of ‘palais’ (EN palace/palate) French ‘palais’ has fourfold ambiguity: – palazzu (EN palace): noun singular – palatu (EN palate): noun singular – palazzi (EN palaces): noun plural – palati (EN palates): noun plural Le palais du calife … Continue reading

Posted in blog | Comments Off on Semantic disambiguation of ‘palais’

Scoring 98,55%: successful Feigenbaum test? No

Scoring 1 – 2/138 = 98,55%. Is it a  successful Feigenbaum test? No, at least due to one gross error: ”fils d’un riche’ should translate ‘figliolu d’un riccu‘ ‘fils’ is threefold ambiguous: figliolu (son), figlioli (sons), fili (threads)

Posted in blog | Comments Off on Scoring 98,55%: successful Feigenbaum test? No