User contributions
Jump to navigation
Jump to search
- 12:11, 27 June 2020 diff hist +92 User:Francis Tyers/Apertium 4 →Engine
- 11:49, 27 June 2020 diff hist +201 Rethinking tokenisation in the pipeline
- 11:39, 27 June 2020 diff hist +1,177 N Rethinking tokenisation in the pipeline Created page with "At the moment tokenisation is done longest-match left-to-right using the morphological analyser and an alphabet defined for breaking up unknown words. This has some advantage..."
- 22:51, 26 June 2020 diff hist +974 N Talk:Surface forms in the pipe Created page with " : But here it has tags, so it's included in the monodix, but with the lemma changed to surface form? : What about CG rules referring to lemmas? -Unhammer User:Khannatanma..."
- 22:51, 26 June 2020 diff hist -597 Surface forms in the pipe →Idea #2 current
- 13:07, 26 June 2020 diff hist +9 Incorporating guessing into Apertium current
- 11:19, 26 June 2020 diff hist +22 Incorporating guessing into Apertium →Another guesser for orthographic variation
- 11:08, 26 June 2020 diff hist +535 Incorporating guessing into Apertium →Another guesser for orthographic variation
- 11:03, 26 June 2020 diff hist +807 Incorporating guessing into Apertium →Guesser for orthographic variation
- 10:17, 26 June 2020 diff hist +476 Incorporating guessing into Apertium
- 12:01, 25 June 2020 diff hist +104 Incorporating guessing into Apertium
- 11:45, 25 June 2020 diff hist +500 Incorporating guessing into Apertium
- 11:20, 25 June 2020 diff hist +176 User:Francis Tyers/Apertium 4
- 16:14, 24 June 2020 diff hist +484 N User talk:Francis Tyers/Apertium 4 Created page with " :: Tanmai Khanna (talk) Isn't that also one of the disadvantages of neural models with strong language models that prefer flu..." current
- 16:13, 24 June 2020 diff hist -262 User:Francis Tyers/Apertium 4 →Research
- 11:58, 24 June 2020 diff hist +72 User:Francis Tyers/Apertium 4
- 11:51, 24 June 2020 diff hist +1,473 N Incorporating guessing into Apertium Created page with "Apertium has a coverage problem. The greater the coverage of the real dictionaries, the more accurate guessing will be. So we wouldn't want to try with a pair that has 80% co..."
- 23:54, 23 June 2020 diff hist +20 User:Francis Tyers/Apertium 4
- 12:55, 23 June 2020 diff hist +255 Surface forms in the pipe →Idea #2
- 12:52, 23 June 2020 diff hist +64 Surface forms in the pipe →Idea #2