Search results

• PMC proposals/Stable version of apertium-sh-sl
  The language pair seems to work OK in the sh→sl sense but not so well in sl→sh (apparently it has not been ''testvocked''). ...is no available workforce. Also, we cannot schedule it as a GSoC task, or, in any case, it should be scheduled as a very early part of a GSoC task that c
  2 KB (380 words) - 22:26, 3 August 2013
• Ideas for Google Summer of Code/Discontiguous multiwords
  ...support. For example 'liggja ekki fyrir' in Icelandic should be translated in English as 'to be not clear', but we cannot have 'liggja fyrir' as a tradit Another example: in Norwegian, "bryta seg inn" means "break in", while "bryta saman" means "collapse". Both these can have an NP between t
  4 KB (632 words) - 12:33, 4 March 2016
• PMC proposals/Apertium membership in EAMT
  =2010/03/20: Apertium membership in EAMT= ...m would have a profile in that web, which is mainly visited by researchers in EAMT, but not only. Currently the EAMT has about 8 corporate members, but o
  2 KB (358 words) - 22:25, 3 August 2013
• Ideas for Google Summer of Code/Corpus-based lexicalised feature transfer
  Make a module that sits somewhere in the Apertium pipeline (somewhere after the lexical selection and before mor ...like definiteness, aspect, evidentiality, impersonal/reflexive pronoun use in Romance languages etc.
  2 KB (262 words) - 11:19, 9 February 2015
• Google Summer of Code/Report 2013
  ===Improvements in lexical-selection module=== ===A Sliding-Window Drop-in Replacement for the HMM Part-of-Speech Tagger in Apertium===
  2 KB (200 words) - 08:21, 13 January 2015
• Tagging guidelines for Spanish
  ...er hundreds, of thousands of words) to 'train' the automatic taggers found in some Apertium language pairs. Getting the right tag for a word is important * [verb] Los domingos ''canto'' en el coro → On Sundays I ''sing'' in the choir.
  4 KB (763 words) - 12:14, 26 September 2016
• Flag diacritics
  ...ed at run-time instead of at compile-time. This lets you have fewer states in your FST (at the cost of some run-time overhead). ...t, but has been reimplemented in [[HFST]] (as well as an experimental mode in [[lttoolbox-java/Flag diacritics]]).
  768 bytes (114 words) - 06:49, 20 October 2014
• Task ideas for Google Code-in/Grow bilingual
  ...m but no reasonable bilingual dictionary (these language pairs are usually in the incubator), for instance apertium-spa-pol ...most frequent unknown words''' (words in the source document which are not in the bilingual dictionaries of the language pair). See below for informatio
  2 KB (320 words) - 15:01, 19 January 2020
• Ideas for Google Summer of Code/Improved bilingual dictionary induction
  Let's suppose we find in the alignments: ...p__n</code> and forms in <code>mois__n</code> to forms in <code>vrem/e__n</code> . For example:
  4 KB (686 words) - 11:05, 27 September 2016
• Ideas for Google Summer of Code/Interface for creating tagged corpora
  ...released pairs and the ones to come: better part-of-speech (POS) taggers. In my experience, training supervised taggers has never been a waste of time b ...nsupervised tagger training|unsupervised manner]] for one of the languages in your pair.
  2 KB (269 words) - 21:26, 5 April 2013
• Ideas for Google Summer of Code/User-friendly lexical selection training
  ...ual dictionaries allow for ambiguous translations, selecting the right one in a context is handled by our [[Lexical selection]] module '''apertium-lex-to ...e should also be regression tests on the driver script, to ensure it works in the face of updates to third-party tools.
  4 KB (541 words) - 13:46, 29 March 2021
• Task ideas for Google Code-in/Add transfer rule
  ...ing (local agreement, gender, number, etc. is inadequate, local word order in a phrase is inadequate, there is a word too much or a word missing, etc.). ...text in L₂ through the pair and find a consistent error in the output text in L₁ that isn't grammatical.
  1 KB (208 words) - 21:39, 15 December 2019
• Raveesh/Application
  Why is it you are interested in machine translation? Why is it that they are interested in the Apertium project?
  1 KB (192 words) - 00:56, 16 March 2014
• Ideas for Google Summer of Code/Flag diacritics in lttoolbox
  Flag diacritics are a method used in the [[HFST]] tools to allow the writer of a transducer to exclude impossibl Some work on [[Flag diacritics]] has already been made in [[lttoolbox-java]].
  1 KB (176 words) - 06:40, 20 October 2014
• Ideas for Google Summer of Code/Sliding-window part-of-speech tagger
  ...pport for unknown words, and also for "forbid" descriptions (not described in the paper). The tagger has a very intuitive interpretation (believe me, eve * Implement the tagger described in the paper.
  2 KB (251 words) - 00:37, 6 April 2013
• Qashqai
  Daniel Huang, Google Code In 2012 <br /> * [http://www.ethnologue.com/show_language.asp?code=qxq Ethnologue report]
  2 KB (205 words) - 22:55, 2 December 2012
• Ideas for Google Summer of Code/Add weights to lttoolbox
  Weights in this page are intuitively defined as larger is worse and two weights can be == Syntaxes for weights in dixes and t?xes and all ==
  5 KB (816 words) - 02:32, 13 February 2018
• Apertium on SliTaz
  Guide prepared by Google Code-In 2014 student Nikita Tsarev. <code>su</code>
  2 KB (281 words) - 02:58, 9 March 2018
• Task ideas for Google Code-in/Comment XML
  And a list in a file (filename given as the first argument to the script) like ...ement. Also, note how :yaa<n> does not comment out the line that has "yaa" in its <l> element.
  3 KB (576 words) - 12:57, 2 January 2016
• Ideas for Google Summer of Code/UD and Apertium integration
  ...-ud` should produce conllu file with LEMMA, POS, FEATs, MISC fields filled in * set up APERTIUM EMBEDDINGS in UDPipe
  1 KB (203 words) - 12:56, 29 January 2018

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