MT that Deceives: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
Many popular MT systems, such as [http://translate.google.com Google Translate] or [http://www.bing.com/translator/ Bing Translator] (for certain languages), are based purely on statistical models. Such models observe word and phrase co-occurrences in parallel texts and try to learn translation equivalents. | Many popular MT systems, such as [http://translate.google.com Google Translate] or [http://www.bing.com/translator/ Bing Translator] (for certain languages), are based purely on statistical models. Such models observe word and phrase co-occurrences in parallel texts and try to learn translation equivalents. | ||
== Negation in English-Czech Translation == | |||
[[File:nemam_kocku.png|thumb|300px|'''Example of an error during phrase extraction.''' The system learns a translation pair ''"nemám" = "I have"'' which has the opposite meaning.]] | [[File:nemam_kocku.png|thumb|300px|'''Example of an error during phrase extraction.''' The system learns a translation pair ''"nemám" = "I have"'' which has the opposite meaning.]] | ||
In some cases, | In some cases, the statistical approach leads to '''systematic errors'''. The picture illustrates a common issue with negation -- in many languages (such as Czech), negation is expressed by a prefix ("''ne''" in this case). Moreover, Czech uses double negatives: the sentence ''Nemám žádnou kočku.'' corresponds to English ''I_do_not_have no cat.'' word by word. Therefore the automatic procedure learns a wrong translation rule ''I have''=''nemám''. Whenever this rule is applied, the meaning of the translation is completely reversed. | ||
== Named Entities == | |||
Other examples of notorious errors include named entities, such as: | Other examples of notorious errors include named entities, such as: | ||
''Jan Novák potkal Karla Poláka. -> John Smith met Charles Pole.'' (The name ''Novák'' is sometimes translated as ''Smith'' as both are examples of very common surnames in the respective language.) | ''Jan Novák potkal Karla Poláka. -> John Smith met Charles Pole.'' (The name ''Novák'' is sometimes translated as ''Smith'' as both are examples of very common surnames in the respective language.) | ||
== Inadequate Modeling of Semantic Roles == | |||
There is also a disconnect when translating between a morphologically poor and a morphologically rich language. While the first tend to express argument roles using '''word order''' (think English), the latter often use '''inflectional afixes'''. A statistical system which simply learn correspondences between words and short phrases then fails to capture the difference in meaning: | There is also a disconnect when translating between a morphologically poor and a morphologically rich language. While the first tend to express argument roles using '''word order''' (think English), the latter often use '''inflectional afixes'''. A statistical system which simply learn correspondences between words and short phrases then fails to capture the difference in meaning: | ||
''Pes dává kočce myš.'' (the dog gives the cat a mouse) | ''Pes dává kočce myš.'' (the dog gives the cat a mouse) | ||
| Line 19: | Line 24: | ||
All of these examples are translated identically by [https://translate.google.com Google Translate] at the moment, even though their meanings are clearly radically different. | All of these examples are translated identically by [https://translate.google.com Google Translate] at the moment, even though their meanings are clearly radically different. | ||
== Numerals == | |||
Translation dictionaries of statistical MT systems are full of potential errors in numbers. TODO | |||
Revision as of 16:34, 30 December 2014
Many popular MT systems, such as Google Translate or Bing Translator (for certain languages), are based purely on statistical models. Such models observe word and phrase co-occurrences in parallel texts and try to learn translation equivalents.
Negation in English-Czech Translation
In some cases, the statistical approach leads to systematic errors. The picture illustrates a common issue with negation -- in many languages (such as Czech), negation is expressed by a prefix ("ne" in this case). Moreover, Czech uses double negatives: the sentence Nemám žádnou kočku. corresponds to English I_do_not_have no cat. word by word. Therefore the automatic procedure learns a wrong translation rule I have=nemám. Whenever this rule is applied, the meaning of the translation is completely reversed.
Named Entities
Other examples of notorious errors include named entities, such as:
Jan Novák potkal Karla Poláka. -> John Smith met Charles Pole. (The name Novák is sometimes translated as Smith as both are examples of very common surnames in the respective language.)
Inadequate Modeling of Semantic Roles
There is also a disconnect when translating between a morphologically poor and a morphologically rich language. While the first tend to express argument roles using word order (think English), the latter often use inflectional afixes. A statistical system which simply learn correspondences between words and short phrases then fails to capture the difference in meaning:
Pes dává kočce myš. (the dog gives the cat a mouse)
Psovi dává myš kočku. (to the dog a mouse is given by the cat)
Psovi dává kočka myš. (to the dog, the cat gives a mouse)
All of these examples are translated identically by Google Translate at the moment, even though their meanings are clearly radically different.
Numerals
Translation dictionaries of statistical MT systems are full of potential errors in numbers. TODO