Search results

Page title matches

• Ideas for Google Summer of Code/Detect hidden unknown words
  '''Detect hidden unknown words by using the probabilities of the HMM-based part-of-speech tagger in ...orms for which there exists at least one lexical form cannot be considered unknown and there is no way to know whether the set of possible lexical forms provi
  2 KB (277 words) - 19:51, 24 March 2020
• Matching unknown words
  ...interchunk, this is quite easy, as each unknown word has the chunk lemma 'unknown', but it's un- or under-documented how this should be done using apertium-t
  2 KB (209 words) - 11:06, 24 March 2012

Page text matches

• Apertium-recursive/Example
  <li>^unknown<NP><m><sg>{^hole<n><sg>/agujero<n><m><sg>$}$</li></ol> <li>^unknown<DP><m><sg>{^a<det><ind><sg>/uno<det><ind><GD><sg>$ ^unknown<NP><m><sg>{^hole<n><sg>/agujero<n><m><sg>$}$}$</li></ol>
  33 KB (6,259 words) - 06:07, 1 June 2023
• Turkic MT Improvements GSoC2019 report
  ...the project, with the help of mentors on Kipchak languages. Most frequent unknown tokens from corpora of each language (mostly consisting of Wikipedia entrie Number of unknown words (marked with a star) in test: 124
  7 KB (798 words) - 18:30, 26 August 2019
• Hectoralos/GSOC 2020 work plan control
  Number of unknown words (marked with a star) in test: 78<br> Percentage of unknown words: 6.61 %<br>
  17 KB (2,274 words) - 06:14, 27 August 2020
• Google Summer of Code/Midterm report 2011
  Number of unknown words (marked with a star) in test: 4 Percentage of unknown words: 1.10 %
  4 KB (404 words) - 00:19, 3 July 2012
• English and Esperanto/Evaluation
  Number of unknown words (marked with a star) in test: 23 Percentage of unknown words: 7,10 %
  39 KB (5,922 words) - 07:37, 20 March 2014
• Uighur and Turkish/GSoC2018 report
  Here is the WER result before I added the unknown words/wrote some CG rules for the text: Number of unknown words (marked with a star) in test:
  5 KB (607 words) - 13:25, 12 August 2018
• Kazakh and Tatar/Work plan
  Number of unknown words (marked with a star) in test: 2 Percentage of unknown words: 0.37 %
  6 KB (728 words) - 19:47, 8 May 2014
• English and Italian/Google Translate
  Number of unknown words (marked with a star) in test: Percentage of unknown words: 0.00 %
  4 KB (563 words) - 16:24, 21 March 2014
• Installation troubleshooting
  .../usr/lib/gcc/x86_64-unknown-linux-gnu/4.8.2/crtendS.o /usr/lib/gcc/x86_64-unknown-linux-gnu/4.8.2/../../../../lib/crtn.o -O3 -mtune=nocona -Wl,-soname -Wl g++: error: /usr/lib/gcc/x86_64-unknown-linux-gnu/4.8.2/../../../../lib/crti.o: No such file or directory
  20 KB (3,153 words) - 08:13, 24 May 2019
• Translation quality statistics
  ...orpus on which further translations will be made. Evaluations not allowing unknown words will give a better indication of "best-case" working of transfer rule ! Translator !! Date !! Version !! Direction !! Unknown<br/>words !! data-sort-type="number"|WER !! data-sort-type="number"|PWER !!
  9 KB (1,233 words) - 09:10, 21 November 2021
• Calculating coverage
  unknown=$(grep -c '/\*' $outfile) known_percent=$(calc -p "round( 100*($total-$unknown-$bidix_unknown)/$total, 3)")
  4 KB (583 words) - 15:18, 10 January 2022
• Named entity recognition
  ...r rules that work on &lt;np&gt;-tagged words do not apply when the word is unknown. Another is that proper nouns can be ambiguous with other, known words, and ==Unknown proper nouns in transfer==
  3 KB (492 words) - 16:52, 10 March 2018
• English and Kazakh
  ...known noun2, prep det unknown adjec noun, prep det unknown noun, sup-adjec unknown nom. ***Another possibility (Aida): detect unknown capitalized words (possible?). We tried with regular expressions but they
  20 KB (2,856 words) - 06:26, 27 May 2021
• Курсы машинного перевода для языков России/Session 7
  ...line coverage for releasing a new prototype translator is around 80%, or 2 unknown words in 10 for a given corpus. This is not enough to make revision practic Number of unknown words (marked with a star) in test:
  18 KB (2,490 words) - 12:00, 31 January 2012
• Helsinki Apertium Workshop/Session 7
  ...line coverage for releasing a new prototype translator is around 80%, or 2 unknown words in 10 for a given corpus. This is not enough to make revision practic Number of unknown words (marked with a star) in test:
  18 KB (2,493 words) - 08:39, 10 May 2013
• Tartu Apertium Course/Session 7
  ...line coverage for releasing a new prototype translator is around 80%, or 2 unknown words in 10 for a given corpus. This is not enough to make revision practic Number of unknown words (marked with a star) in test:
  18 KB (2,493 words) - 10:59, 30 October 2015
• Why we trim
  ...d into misunderstanding the content, instead of observing that there is an unknown word. ...rmous increase in transfer complexity – all tags have to be presumed to be unknown, and developer time is wasted on bug-hunting and workarounds instead of imp
  4 KB (679 words) - 16:06, 3 May 2020
• Norwegian Nynorsk and Norwegian Bokmål
  Number of unknown words (marked with a star) in test: 653 Percentage of unknown words: 17.48 %
  23 KB (3,704 words) - 11:56, 16 December 2020
• Apertium and Constraint Grammar
  ==Matching unknown words in Apertium== lttoolbox prepends a star to unknown words, so you can match unknown words using a simple regexp matching that star:
  7 KB (1,116 words) - 20:57, 2 April 2021
• Constraint-based lexical selection module
  ...the OR operation, the rules would try to match precisely a sequence of one unknown word followed by one known one. ====Matching an unknown word====
  19 KB (2,820 words) - 15:26, 11 April 2023

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