Comments on: Measuring Quality http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/ ideas on translation... Thu, 12 Nov 2009 15:39:46 +0000 http://wordpress.com/ hourly 1 By: Merlin: Translation News, Services & Directory » Blog Archive » Degrees of Equivalence (≠ ≈ = ≡) http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3612 Merlin: Translation News, Services & Directory » Blog Archive » Degrees of Equivalence (≠ ≈ = ≡) Thu, 07 May 2009 22:00:19 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3612 [...] of tools, such as the ISO quality standard mentioned in the previous post, or various attempts to measure quality. The same can be said of the use of corpus tools or machine translation in the translation process, [...] [...] of tools, such as the ISO quality standard mentioned in the previous post, or various attempts to measure quality. The same can be said of the use of corpus tools or machine translation in the translation process, [...]

]]> By: Degrees of Equivalence (≠ ≈ = ≡) « transubstantiation http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3352 Degrees of Equivalence (≠ ≈ = ≡) « transubstantiation Mon, 01 Dec 2008 14:58:28 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3352 [...] of tools, such as the ISO quality standard mentioned in the previous post, or various attempts to measure quality. The same can be said of the use of corpus tools or machine translation in the translation process, [...] [...] of tools, such as the ISO quality standard mentioned in the previous post, or various attempts to measure quality. The same can be said of the use of corpus tools or machine translation in the translation process, [...]

]]> By: Merlin: Translation News, Services & Directory » Blog Archive » ISO 9002 - Translation Standard? http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3346 Merlin: Translation News, Services & Directory » Blog Archive » ISO 9002 - Translation Standard? Sun, 23 Nov 2008 23:59:59 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3346 [...] working from home. The final question: can quality in any way be assured (and measured)? A previous post also dealt with this subject. The answer most certainly lies in the affirmative, although this is [...] [...] working from home. The final question: can quality in any way be assured (and measured)? A previous post also dealt with this subject. The answer most certainly lies in the affirmative, although this is [...]

]]> By: ISO 9002 - Translation Standard? « transubstantiation http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3344 ISO 9002 - Translation Standard? « transubstantiation Sun, 23 Nov 2008 12:33:53 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3344 [...] working from home. The final question: can quality in any way be assured (and measured)? A previous post also dealt with this subject. The answer most certainly lies in the affirmative, although this is [...] [...] working from home. The final question: can quality in any way be assured (and measured)? A previous post also dealt with this subject. The answer most certainly lies in the affirmative, although this is [...]

]]> By: transubstantiation http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3266 transubstantiation Sun, 10 Aug 2008 06:03:25 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3266 Indeed! Indeed!

]]> By: blog.rightreading.com » Friday roundup http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3265 blog.rightreading.com » Friday roundup Fri, 08 Aug 2008 13:03:20 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3265 [...] Assessing translations statistically : What would MoFo’s curators say? [...] [...] Assessing translations statistically : What would MoFo’s curators say? [...]

]]> By: transubstantiation http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3262 transubstantiation Sun, 27 Jul 2008 19:12:22 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3262 Exactly! Thank you. Exactly!
Thank you.

]]> By: Raf Uzar http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3261 Raf Uzar Sun, 27 Jul 2008 19:11:30 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3261 N-grams, actually. I've used n-grams, lexical clusters, that is... Raf N-grams, actually. I’ve used n-grams, lexical clusters, that is…
Raf

]]> By: transubstantiation http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3259 transubstantiation Wed, 16 Jul 2008 17:25:05 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3259 Interesting work by Raf Uzar in Poland has demonstrated that it is possible to extract purely statistical information from a translation that says a lot about the 'potential' quality of a text. The logic is that if a particular text displays an atypical amount of a particular structure or pattern, we can assume that the text is probably poor in quality. For example, a translation that uses an above average amount of indefinite articles probably demonstrates the translator's inability to use the article. In other words, texts that do not gravitate towards the average are in some way 'atypical' and in all probability of poor quality. Idiosyncrasies, linguistic extravagances and eccentricities are in fact exceedingly rare in language (from a statistical point of view). Interesting work by Raf Uzar in Poland has demonstrated that it is possible to extract purely statistical information from a translation that says a lot about the ‘potential’ quality of a text. The logic is that if a particular text displays an atypical amount of a particular structure or pattern, we can assume that the text is probably poor in quality. For example, a translation that uses an above average amount of indefinite articles probably demonstrates the translator’s inability to use the article.

In other words, texts that do not gravitate towards the average are in some way ‘atypical’ and in all probability of poor quality. Idiosyncrasies, linguistic extravagances and eccentricities are in fact exceedingly rare in language (from a statistical point of view).

]]> By: MT http://transubstantiation.wordpress.com/2008/07/15/measuring-quality/#comment-3258 MT Wed, 16 Jul 2008 17:08:31 +0000 http://transubstantiation.wordpress.com/?p=91#comment-3258 I just don't think any enterprise that links computers to generating, translating, or reviewing language works or can work. Nothing I've seen from that field to date is even remotely promising, really, and even somethings like TMs have even done injury to the practice of translation and lowered quality in some ways. I just don't see how numerically based quality assessment can work--mainly because "quality" depends largely on subjective elements. Even deciding what anchors to pick is subjective. Indeed, a translation that a computer might otherwise greenlight the quality of may in reality be abysmal simply because it's too close to the original, or too clunky once read by humans. Computers just can't deal with language properly, and they never will. I just don’t think any enterprise that links computers to generating, translating, or reviewing language works or can work. Nothing I’ve seen from that field to date is even remotely promising, really, and even somethings like TMs have even done injury to the practice of translation and lowered quality in some ways. I just don’t see how numerically based quality assessment can work–mainly because “quality” depends largely on subjective elements. Even deciding what anchors to pick is subjective. Indeed, a translation that a computer might otherwise greenlight the quality of may in reality be abysmal simply because it’s too close to the original, or too clunky once read by humans. Computers just can’t deal with language properly, and they never will.

]]>