Debian Codegraph @

NEWS

raw
1 May 5, 2023
2 * Release 0.3.0
3 * Change in generated Orthography - Adapted to the official orthograpy of the Academia Aragonesa de la Lengua (https://www.academiaaragonesadelalengua.org/sites/default/files/ficheros-pdf/Ortograf%C3%ADa%20de%20l%27aragon%C3%A9s_web_an.pdf)
4 * Keeps analysis compatibility with previous orthography (apertium-arg)
5 * New entries added.
6 * Minor fixes performed.
7 * Bilingual dictionary:
8 > 24405 entries (6934 proper nouns).
9 * Main pending issues: improve disambiguation with CG, add support for generating dialectal preferences
10
11 Jan 08, 2021
12 * Release 0.2.0
13 * Changed arg.prob file (in apertium-arg)
14 * Adapted to changes in apertium-cat and apertium-arg
15 * Added support for new np labels and acronyms
16 * Definite articles generated according to "Gramatica Basica de l'Aragonés" neutral standard paradigm.
17 * Improved apostrophation rules in post generation. Fix problems with "de + en (prep)".
18 * Added support for superlatives with "muito/muit/molt"
19 * Minor fixes performed
20 * Bilingual dictionary:
21 > 24386 entries (6930 proper nouns)
22
23 Jan 16, 2016
24 * Initial release (0.1.0), beta
25 * Operative bidirectional release.
26 * Features:
27 * Uses monolingual packages apertium-cat and apertium-arg (separated monolingual and bilingual data).
28 * Trimming of the monolingual dictionary (in both directions).
29 * Lexical selection support (not used yet).
30 * Monolingual dictionaries:
31 Aragonese (apertium-arg): > 546 paradigms, > 21073 lemmae (of which, 8047 proper nouns), including 1921 multi-words.
32 Catalan (apertium-cat): > 559 paradigms, > 41143 lemmae (of which, 8341 proper nouns), including 4115 multi-words.
33 * Bilingual dictionary: 24110 entries. Open categories crossed from apertium-spa-arg (ver 0.4.1) and apertium-es-ca. Some closed categories incomplete.
34 * Naïve coverage:
35 Aragonese: From 87.7% in an.wikipedia to 89.2% in a corpus of narrative texts.
36 Catalan: From 87.6% in Catalan corpus at trunk/apertium-eo-ca/tekstaro/ca.crp.txt to 93.2% at trunk/apertium-es-ca/ca-tagger-data/ca.tagged.txt
37 * Translation performance: Catalan to Aragonese (50 first sentences of ca.crp.txt): WER = 19.37% (PER=17.85%); WER (unknown removed) = 15.48% (PER=13.96%). Unknown words: 11.86%. Free rides: 32.69%.
38 * Dialectal support: Analysis of Aragonese dialectal forms supported. Valencian forms are analyzed, but not generated.
39 * Main pending Issues:
40 * Improve on coverage.
41 * Work on transfer.
42 * Develop lexical selection rules