Difference between revisions of "Icelandic and English"
Jump to navigation
Jump to search
Line 7: | Line 7: | ||
* Use IceParser to parse a corpus and extract the most frequent patterns in terms of chunks/phrases (lists of coarse POS tags) and phrase patterns (in terms of chunks/phrases). |
* Use IceParser to parse a corpus and extract the most frequent patterns in terms of chunks/phrases (lists of coarse POS tags) and phrase patterns (in terms of chunks/phrases). |
||
* Merge analysed corpus (IceMorphy full-form list) with Apertium dictionary — will require matching partial information to paradigms... perhaps use [[extract]] ? |
* Merge analysed corpus (IceMorphy full-form list) with Apertium dictionary — will require matching partial information to paradigms... perhaps use [[extract]] ? |
||
* In the Icelandic analyser: |
* In the Icelandic analyser (<code>apertium-is-en.is.dix</code>): |
||
** Fix verb paradigms... most are missing |
** Fix verb paradigms... most are missing: |
||
*** Participle forms (declensions) and infinitives |
|||
⚫ | |||
*** Active and middle voice distinction (see file <code>dev/is-tags.mapping.txt</code> for tag mapping details) |
|||
⚫ | |||
==Resources== |
==Resources== |
Revision as of 15:54, 12 February 2009
Pending tasks
Tag a corpus with IceTaggerand train theapertium-tagger
- Post-edit automatically-generated bilingual dictionaries
- Try and convert some IceTagger constraint rules to work in constraint grammar
- Use IceParser to parse a corpus and extract the most frequent patterns in terms of chunks/phrases (lists of coarse POS tags) and phrase patterns (in terms of chunks/phrases).
- Merge analysed corpus (IceMorphy full-form list) with Apertium dictionary — will require matching partial information to paradigms... perhaps use extract ?
- In the Icelandic analyser (
apertium-is-en.is.dix
):- Fix verb paradigms... most are missing:
- Participle forms (declensions) and infinitives
- Active and middle voice distinction (see file
dev/is-tags.mapping.txt
for tag mapping details)
- Check declensions for adjectives to see if any parts can be factored out (e.g. the weak/strong inflection)
- Fix verb paradigms... most are missing:
Resources
Corpora
- Mediawiki l10n, KDE4, OpenSubtitles, etc. — from OPUS (~60k sentences)
- Parliamentary Acts (?? sentences)
Bilingual dictionaries
- Wikipedia interwiki (~1,100 entries)
- Freelang (~1,000 entries)
- Wiktionary (en) (~3,200 entries)
- An Icelandic-English Dictionary (Old Icelandic, 1876 — Public Domain)
- And here
- Wordbank at ismal.hi.is (licence unknown)
- was moved to here
Example phrase
- Hver maður er borinn frjáls og jafn öðrum að virðingu og réttindum.
IceFormat
Hver foken maður nken er sfg3en borinn sþgken frjáls lkensf og c jafn aa öðrum fokfþ að c virðingu nveþ og c réttindum nhfþ . .
{*SUBJ> [NP Hver foken maður nken NP] *SUBJ>} [VPb er sfg3en VPb] {*COMP< [VPp borinn sþgken VPp] *COMP<} {*COMP< [APs [AP frjáls lkensf AP] [CP og c CP] [AP jafn lkensf AP] APs] *COMP<} [NP öðrum fokfþ NP] [SCP að c SCP] [NPs [NP virðingu nveþ NP] [CP og c CP] [NP réttindum nhfþ NP] NPs]
Apertium
^Hver<prn><ind><m><sg><nom>$ ^maður<n><m><sg><nom><ind>$ ^vera<vbser><pri><p3><sg>$ ^bera<vblex><pp><m><sg><nom>$ ^frjáls<adj><sta><pst><m><sg><nom>$ ^og<cnjcoo>$ ^jafn<adj><sta><pst><m><sg><nom>$ ^annar<prn><ind><m><pl><dat>$ ^að<pr>$ ^virðing<n><f><sg><dat><def>$ ^og<cnjcoo>$ ^réttindi<n><nt><pl><dat><ind>$ ^.<sent>$
^prn_nom<SN><@SUBJ→>{^Hver<prn><ind><m><sg><nom>$ ^maður<n><m><sg><nom><ind>$}$ ^verb<SV>{^vera<vbser><pri><p3><sg>$ ^bera<vblex><pp><m><sg><nom>$}$ ^adj_cc_adj<SA>{^frjáls<adj><sta><pst><m><sg><nom>$ ^og<cnjcoo>$ ^jafn<adj><sta><pst><m><sg><nom>$}$ ^nom<SN>{^annar<prn><ind><m><pl><dat>$}$ ^að<Prep>{^að<pr>$}$ ^nom_cc_nom{^virðing<n><f><sg><dat><def>$ ^og<cnjcoo>$ ^réttindi<n><nt><pl><dat><ind>$}$
See also
- Pending tests — Examples for testing new rules
- Regression tests — Examples of working phrase translations.