Difference between revisions of "Bengali and English/Transfer"

From Apertium
Jump to navigation Jump to search
(Blanked the page)
 
Line 1: Line 1:
== Rules(en-bn.t1x) ==
 
 
1. '''NOM''' (''chunk'': '''nom''')
 
''Pattern'' : noun/proper noun
 
''Action'' : assign <p3><infml> to person
 
''Chunk'' : nom<SN><[gen]><[nbr]><nom>
 
''Comment'' : catches the nominals
 
''Example'' : "Bangladesh" = "^nom<SN><mf><sg><nom>{^বাংলাদেশ<np><top><2><3><4>$}$"
 
 
 
2. '''ADJ NOM''' (''chunk'': '''adj_nom''')
 
''Pattern'' : adjective proper-noun
 
''Action'' :
 
''Chunk'' : adj_nom<SN><[gender]><[number]><nom>
 
''Comment'' : catches nominals with adjective
 
''Example'' : "Beautiful Bangladesh" = "^adj_nom<SN><mf><sg><nom>{^সুন্দর<adj><sint><mf>$ ^বাংলাদেশ<np><top><2><3><4>$}$"
 
 
 
3. '''ADJ''' (''chunk'': '''adj''')
 
''Pattern'' : adjective
 
''Action'' :
 
''Chunk'' : adj<SN><[adj attribute]><[gender]><nom>
 
''Comment'' : catches adjectives
 
''Example'' : "Beautiful" = "^adj<SN><adj><sint><mf>{^সুন্দর<2><3>$}$"
 
 
 
4. '''ART NOM''' (''chunk'': '''art_nom''')
 
''Pattern'' : definitive determinant (i.e. 'The')
 
''Action'' : assign <p3><infml> to person, when nominal is noun and singular mark as 'definitive'
 
''Chunk'' : art_nom<SN><[gender]><[number]><nom>
 
''Comment'' : catches nominals with article ('The')
 
''Example'' : "The Sundarbans" = "^art_nom<SN><m><sg><nom>{^সুন্দরবন<np><top><2><3><4>$}$"
 
 
 
5. '''DET NOM''' (''chunk'': '''det_nom''')
 
''Pattern'' : determinant nominal
 
''Action'' : fix determiner tag, assign <p3><infml> to person
 
''Chunk'' : det_nom<SN><[gender]><[number]><nom>
 
''Comment'' : catches nominals with determiners
 
''Example'' : "Our Sundarbans" = "^det_nom<SN><m><sg><nom>{^আমাদের<det><gen>$ ^সুন্দরবন<np><top><2><3><4>$}$"
 
 
 
6. '''DET ADJ NOM''' (''chunk'': '''det_adj_nom''')
 
 
7. '''PRNSUBJ''' (''chunk'': '''prnsubj''')
 
 
8. '''PRNREF''' (''chunk'': '''prnref''')
 
 
9. '''VBSER VBLEX''' (''chunk'': '''vbser_vblex''')
 
 
10. '''VBHAVER VBLEX''' (''chunk'': '''vbhaver_vblex''')
 
 
11. '''VAUX VBLEX''' (''chunk'': '''vaux_vblex''')
 
 
12. '''FTAUX BE VBLEX''' (''chunk'': '''ftaux_be_vblex''')
 
 
13. '''VBSER PRES''' (''chunk'': '''vbser_pri''')
 
 
14. '''VBSER PAST''' (''chunk'': '''vbser_past''')
 
 
15. '''VERB CONJ''' (''chunk'': '''verbcj''')
 
 
16. '''VBSER PRES''' (''chunk'': '''vbser_pres''')
 
 
17. '''VBHAVER VBSER VBLEX''' (''chunk'': '''vbhaver_vbser_vblex''')
 
 
18. '''NUM NOM''' (''chunk'': '''num_nom''')
 
 
19. '''POST''' (''chunk'': '''post''')
 
 
== Issues(en-bn) ==
 
 
* In the rule "SN SV SN" in t2x, case for the last SN is forced <obj>. This is not right all the time; say,
 
"I eat fish" → "আমি মাছকে খাই"
 
this should be "আমি মাছ খাই", whereas,
 
"I love you" → "আমি আপনাকে ভালবাসি"
 
is ok with case <obj>.
 
 
 
* About the future perfect tense, it should like this:
 
"I shall have eaten rice" → "আমি ভাত খেয়ে থাকব"
 
But we don't have inflections for the verb 'খ/া' for 'েয়ে থাকব'
 
 
 
* May be some tagger problem; running the following for pretransfer output with "Zaher plays football":
 
echo "Zaher plays football" | /usr/local/bin/lt-proc /usr/local/share/apertium/apertium-bn-en/en-bn.automorf.bin | \
 
/usr/local/bin/apertium-tagger -g /usr/local/share/apertium/apertium-bn-en/en-bn.prob |/usr/local/bin/apertium-pretransfer
 
outputs this:
 
^Zaher<np><ant><m><sg>$ ^play<n><pl>$ ^football<n><sg>$
 
where 'plays' should be analyzed as verb (play<vblex><pri><p3><sg>). And for this reason, we get such outputs:
 
"Zaher plays football" → "জাহের নাটকগুলো ফুটবল"
 
 
 
 
[[Category:Bengali and English]]
 

Latest revision as of 19:17, 10 August 2011