Search results

• Online Apertium Workshop 2020/Ugly hacks
  ...ing this whole process that trimming is behind many quality issues in some apertium dix and it can infect other dix even if trimming. Here's a non-exhaustive l ...m dix so I see these oftener than most... I don't mean to point fingers at apertium-eng devs but I had decent amount of memorable problems with it working on W
  4 KB (756 words) - 13:37, 2 July 2020
• Compounds
  ...[[Germanic language]]s and Proto-Indo-Iranian languages like [http://wiki.apertium.org/wiki/Sanskrit Sanskrit], make long compound words with low frequency th ...Poŝtelefono, poŝa+telefono (pocket phone). Bonkvalita, bona+kvalita (good quality). Diaro, dio+aro (god collection),
  16 KB (2,689 words) - 09:07, 6 April 2021
• Named entity recognition
  The module [[apertium-pn-recogniser]] detects proper nouns in the input and marks them as unknown ...the transfer modules. Option -p is needed in the tagger, so a version from Apertium greater or equal to 3.1.0 is needed.
  3 KB (492 words) - 16:52, 10 March 2018
• Ideas for Google Summer of Code/Improvements to target-language tagger training
  ...ning. This means that it tunes the parameters of an HMM model based on the quality of the translations through the whole system. To do so, it segments the sou * The first part consists of making apertium-tagger-training-tools able to segment using any-level of structural transfe
  2 KB (260 words) - 19:55, 24 March 2020
• Corpora formats
  The apertium project uses corpora to test coverage, translation, and a number of other t ...an idea Jonathan has for implementing a standard corpora format for use by apertium.
  5 KB (813 words) - 00:08, 28 December 2011
• Ideas for Google Summer of Code/Improving support for non-standard text input
  * Translate them with Apertium * Come up with examples of non-standard features that effect translation quality
  902 bytes (121 words) - 12:50, 10 March 2014
• Continuous Integration
  However, even with the above criteria, it's quite possible that translation quality overall worsens. * [[Travis settings for Apertium]]
  2 KB (266 words) - 10:26, 22 February 2017
• Apertium separable/report2017
  The purpose of this project is to allow Apertium language-pair developers to better translate "seperable" or "discontiguous" ...en the transducer would output the re-ordered words for better translation quality.
  1 KB (205 words) - 18:36, 15 November 2017
• Ideas for Google Summer of Code/User-friendly lexical selection training
  ...e right one in a context is handled by our [[Lexical selection]] module '''apertium-lex-tools'''. We can either write rules manually, or word-align and train o ** check if it improves quality (using parallell corpora)
  4 KB (541 words) - 13:46, 29 March 2021
• Quality control framework/Personal
  = Apertium Quality Control Framework =
  518 bytes (76 words) - 16:01, 22 June 2011
• Quality control framework
  #REDIRECT [[Apertium-quality]]
  30 bytes (2 words) - 14:47, 19 August 2011
• Lexical feature transfer - Second report
  ...ge translations and labeled. There was some improvement in the translation quality, however, there were many wrong predictions as a result of the small traini ...d, even though the testing set is smaller, is because the translation from apertium is much closer to the original text in terms of synonym use, grammatical st
  5 KB (620 words) - 12:21, 27 July 2012
• Pourquoi nous tronquons
  Dans les paires de langues Apertium, on conserve les dictionnaires unilingues et bilingues ''tronqués'', ainsi ...ndex.php/Session_7 Session 7: Consistance des données et qualité] sur wiki.apertium.eu
  5 KB (789 words) - 08:43, 8 October 2014

View (previous 20 | next 20) (20 | 50 | 100 | 250 | 500)