Difference between revisions of "Indonesian and Malaysian"
Jump to navigation
Jump to search
Line 5: | Line 5: | ||
{|class=wikitable |
{|class=wikitable |
||
|- |
|- |
||
! Week !! Dates !! Activities !! Coverage reached ( |
! Week !! Dates !! Activities !! Coverage reached (wp) !! Evaluation !! WER reached |
||
|- |
|- |
||
| 0 || 23/04—21/05 || Translating the story to get a baseline WER. || - || 500 words || 4.68% |
| 0 || 23/04—21/05 || Translating the story to get a baseline WER. || - || 500 words || 4.68% |
||
Line 11: | Line 11: | ||
| 1 || 21/05—27/05 || Working on Indonesian analyzer/generator. || - || - || - |
| 1 || 21/05—27/05 || Working on Indonesian analyzer/generator. || - || - || - |
||
|- |
|- |
||
| 2 || 28/05—03/06 || Working on Indonesian analyzer/generator.<br/>Translating Malaysian wikipedia articles to Indonesian. || 72.9%, 29,9% || - || - |
| 2 || 28/05—03/06 || Working on Indonesian analyzer/generator.<br/>Translating Malaysian wikipedia articles to Indonesian to get a parallel corpus. Bilingual dictionaries will be [[Extracting bilingual dictionaries with Giza++|extracted]] from the corpus. || 72.9%, 29,9% || - || - |
||
|- |
|- |
||
| 3 || 04/06—10/06 || Translating Malaysian wikipedia articles to Indonesian.<br/>Working on Malaysian analyzer/generator. || , 46.4% || - || - |
| 3 || 04/06—10/06 || Translating Malaysian wikipedia articles to Indonesian.<br/>Working on Malaysian analyzer/generator. || , 46.4% || - || - |
Revision as of 20:20, 10 June 2012
This is a language pair translating between Indonesian and Malaysian.
Contents
Work Plan
Week | Dates | Activities | Coverage reached (wp) | Evaluation | WER reached |
---|---|---|---|---|---|
0 | 23/04—21/05 | Translating the story to get a baseline WER. | - | 500 words | 4.68% |
1 | 21/05—27/05 | Working on Indonesian analyzer/generator. | - | - | - |
2 | 28/05—03/06 | Working on Indonesian analyzer/generator. Translating Malaysian wikipedia articles to Indonesian to get a parallel corpus. Bilingual dictionaries will be extracted from the corpus. |
72.9%, 29,9% | - | - |
3 | 04/06—10/06 | Translating Malaysian wikipedia articles to Indonesian. Working on Malaysian analyzer/generator. |
, 46.4% | - | - |
4 | 11/06—17/06 | Working on Malaysian analyzer/generator and bidix. | - | - |
Morphology
Verb-forming affixes
Affix | Function | Example | Segmentation | Lemma | Translation | Analysis |
---|---|---|---|---|---|---|
meN- | active voice | membaca | meN+baca | baca (v.read) | v.read | baca<vblex><actv> |
di- | to be done by someone | dibaca | di+baca | baca (v.read) | read [by someone] | baca<vblex><di> |
ber- | to convert noun to verb | berdiri | ber+diri | diri (n.self) | stand | diri<n><vblex><ber> |
ber-R | bermain-main | ber+main+main | main (v.play) | playing around | main<vblex><ber><pl> | |
ber-an | reciprocal action | bertabrakan | ber+tabrak+an | tabrak (v.hit) | collide | tabrak<vblex><ber><an> |
ber-R-an | reciprocal action | berpeluk-pelukkan | ber+peluk+peluk+kan | peluk (v.hug) | hugging each other | peluk<vblex><ber><pl><an> |
ter- | unintentional action | termakan | ter+makan | makan (v.eat) | eaten (unintentionally) | makan<vblex><ter> |
ter-R | terapung-apung | ter+apung+apung | apung (v.float) | float | apung<vblex><ter><pl> | |
meN-i | mendatangi | meN+datang+i | datang (v.come) | come (to a place) | datang<vblex><actv><i> | |
di-i | passive | didatangi | di+datang+i | datang (v.come) | visited | datang<vblex><di><i> |
meN-kan | causative | mendatangkan | meN+datang+kan | datang (v.come) | make someone come | datang<vblex><actv><kan> |
di-kan | causative, passive | didatangkan | di+datang+kan | datang (v.come) | imported | datang<vblex><di><kan> |
memper- | to make less or more | memperbesar | meN+per+besar | besar (a.big) | make something bigger | besar<adj><vblex><actv><per> |
diper- | to make less or more, passive | diperbesar | di+per+besar | besar (a.big) | made bigger | besar<vblex><di><per> |
memper-kan | to change noun to transitive verb | mempertanyakan | meN+per+tanya+kan | tanya (n.question) | v.question | tanya<n><vblex><actv><per-kan> |
diper-kan | dipertanyakan | di+per+tanya+kan | tanya (n.question) | questioned | tanya<n><vblex><di><per-kan> |
Adjective formation
Affix | Function | Example | Segmentation | Lemma | Translation | Analysis |
---|---|---|---|---|---|---|
ter- | superlative | terbesar | ter+besar | besar (a.big) | biggest | besar<adj><ter> |
se- | same | sebesar | se+besar | besar (a.big) | as big as | besar<adj><se> |
Noun formation
Affix | Function | Example | Segmentation | Lemma | Translation | Analysis |
---|---|---|---|---|---|---|
-an | entity | tulisan | tulis+an | tulis (v.write) | writings | tulis<vblex><n><sg><an> |
peN- | actor | penjual | peN+jual | jual (v.sell) | seller | jual<vblex><n><sg><peN> |
ke-an | abstract | kepandaian | ke+pandai+an | pandai (a.intelligent) | intelligence | pandai<adj><n><sg><ke-an> |
peN-an | process | pengiriman | pe+kirim+an | kirim (v.send) | delivery | kirim<vblex><n><sg><peN-an> |
per-an | theme | pertokoan | per+toko+an | toko (n.store) | shopping centre | toko<n><sg><per-an> |