Search results

There is a page named "Transfer rules" on this wiki. See also the other search results found.

• Germanic languages
  ...rs for each language, and then making individual dictionaries and transfer rules for every pair. The current status of these goals is listed below. ...th the addition of a [[Constraint Grammar|CG]] for language X and transfer rules / dictionary for the pair X→Y. Below is listed development progress for e
  32 KB (3,684 words) - 06:16, 28 December 2018
• Translation quality statistics
  ...own words will give a better indication of "best-case" working of transfer rules. (Stats pages currently do not show number of CG or transfer rules.)
  9 KB (1,260 words) - 10:23, 3 June 2024
• Bosnian-Croatian-Montenegrin-Serbian and Slovenian/TODOs for the article
  <spectie> --- maybe make LRX rules for the differences described on the wikipedia page http://en.wikipedia.org * transfer, and transfer examples in both directions (Hrvoje)
  2 KB (223 words) - 15:58, 23 April 2013
• Scottish Gaelic and Irish
  * Making constraint grammar rules more CG-like * Write rules to do initial mutations for generation.
  2 KB (381 words) - 09:59, 8 May 2011
• Transducers as flag diacritics and their topology learning
  ...nd finally emit an epsilon symbol as flag diacritics defined by constraint rules do, or process the input and output the transducer's computation. ...at makes possible to avoid the possibly infinite definition of not regular rules in a dictionary to work with more complex forms of inflection.
  6 KB (842 words) - 06:41, 20 October 2014
• Apertium-uzb
  ...separate lexcs and twols (.lat and .cyr) with the continuation lexica and rules and all, though you may be able to get by with one twol considering how sim ...ambiguation rules to be as script-agnostic as possible. For word-specific rules, make a version for each script?
  4 KB (601 words) - 17:49, 8 March 2018
• Tatar and Russian
  * Constraint grammar of Tatar containing at least 1000 rules, which makes 90-95% of all words unambiguous, with at least 95% retaining t |colspan="4" style="text-align:center"| transfer rules for pending wiki tests (focus on phrases and clauses, not single words)
  8 KB (1,006 words) - 12:48, 9 March 2018
• Apertium-eng-srn
  |Sranan rlx rules |Sranan-English t1x rules
  4 KB (543 words) - 21:59, 3 September 2017
• Ideas for Google Summer of Code/Apertium FST CG
  ...yntax to other Apertium modules (dictionaries, lexical selection, transfer rules, etc). ...] could be used as reference implementation, as it handles similar type of rules, but it looks to the source language (left part) to decide over the target
  1 KB (234 words) - 19:48, 24 March 2020
• Meta-evaluation
  ** Number of disambiguation rules ** Number of lexical selection rules
  2 KB (246 words) - 02:32, 1 June 2019
• Ideas for Google Summer of Code/Add weights to lttoolbox
  # lexical transfer # structural transfer
  5 KB (816 words) - 02:32, 13 February 2018
• Constructions
  ...ok really like multiword expressions, other times they look like syntactic transfer, most of them have probably have some kind of fixed lexical element. ...sy to translate word-for-word, but also quite annoying to have in transfer rules.
  1 KB (207 words) - 07:51, 9 October 2014
• Sorani/Verbs
  ...tax in analysis, the clitics could simply be output in order, and transfer rules written accordingly. ...best to have the same pattern output regardless of clitic, for the sake of transfer. The third person singular as object is implied when there is no pronominal
  2 KB (357 words) - 12:40, 1 October 2016
• Google Summer of Code/Application 2019
  To transfer to the application Apertium is a shallow-transfer machine translation system, which uses finite state transducers for all of
  8 KB (1,230 words) - 06:02, 5 February 2019
• Weights in the pipeline
  transfer: Maybe transfer could combine them and output a single one.
  2 KB (307 words) - 14:29, 22 June 2020
• Incorporating guessing into Apertium
  * Bilingual transfer For the bilingual transfer things are more difficult, but one could imagine using techniques such as t
  4 KB (558 words) - 13:07, 26 June 2020
• Google Summer of Code/Application 2020
  To transfer to the application Apertium is a shallow-transfer machine translation system, which uses finite state transducers for all of
  8 KB (1,248 words) - 15:51, 17 February 2021
• Slovenian and Spanish
  * Think of rules to fix frequent disambiguation problems ;Slovenian→Spanish transfer
  4 KB (472 words) - 16:41, 7 June 2011
• Apertium-viewer
  * The tool validates XML dictionary and transfer files. * Support for trace of transfer/interchunk - with links to the applied rules - also works for online modes
  10 KB (1,606 words) - 20:54, 20 February 2022
• Kazakh and Russian/Pending tests
  # fix tags of "be" in transfer # transfer rules to get tags from beAdjVerb to new be{{tag|v}}
  14 KB (567 words) - 20:03, 24 March 2020

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