Difference between revisions of "Hindi and English"

From Apertium
Jump to navigation Jump to search
 
(28 intermediate revisions by 5 users not shown)
Line 1: Line 1:
 
{{TOCD}}
 
{{TOCD}}
  +
  +
==English and Hindi for GSoC==
  +
  +
English–Hindi is sometimes/often discouraged as a GSoC project because:
  +
  +
# it has been done unsuccessfully at least 3 times already;
  +
# it's hard;
  +
# Google already does it well (the GSoC project is "reaching state-of-the-art");
  +
# ...
   
 
==Todo list==
 
==Todo list==
 
{{main|/Work plan|Work plan}}
 
{{main|/Work plan|Work plan}}
   
* Check that [https://apertium.svn.sourceforge.net/svnroot/apertium/branches/xupaixkar/rasskaz/en.txt the story] is correctly translated from English to Hindi and that there are no missing sentences.
+
* <s>Check that [https://apertium.svn.sourceforge.net/svnroot/apertium/branches/xupaixkar/rasskaz/en.txt the story] is correctly translated from English to Hindi and that there are no missing sentences.</s>
* Fix spelling errors in the story.
+
* <s>Fix spelling errors in the story.</s>
* Add other personal pronouns on the model of 'I' -- in both the Hindi dictionary and the bilingual dictionary.
+
* <s>Add other personal pronouns on the model of 'I' -- in both the Hindi dictionary and the bilingual dictionary.</s>
* Come up with short example sentences (they should include a verb) for common postpositions "with the cat" "under the table". etc.
+
* <s>Come up with short example sentences (they should include a verb) for common postpositions "with the cat" "under the table". etc.</s>
  +
* Every word in the bidix should have a POS tag
  +
* <s>Every noun on the Hindi side should have gender.</s>
  +
* Adjectives in English in the bidix should be marked for 'sint'.
  +
* Check if there are any forms missing from [[#Verb_conjugation]]
   
 
==Disambiguation==
 
==Disambiguation==
Line 27: Line 40:
 
</pre>
 
</pre>
   
Postposition can be simple or ke + adv/noun.
+
Postposition can be simple or + adv/noun.
   
 
===Genitive phrase===
 
===Genitive phrase===
Line 33: Line 46:
 
<pre>
 
<pre>
   
SN-obl ke-$GEN.$NBR.nom SN-$GEN.$NBR.nom
+
SN-obl -$GEN.$NBR.nom SN-$GEN.$NBR.nom
   
 
</pre>
 
</pre>
  +
  +
===Verb conjugation===
  +
<div style="float:right">
  +
{|class=wikitable
  +
! Tag !! Description
  +
|-
  +
| {{tag|impf}} || Imperfective participle
  +
|-
  +
| {{tag|perf}} || Perfective participle
  +
|-
  +
| {{tag|inf}} || Infinitive
  +
|-
  +
| {{tag|prs}} || Subjunctive
  +
|-
  +
| {{tag|fut}} || Future
  +
|-
  +
| {{tag|imp}} || Imperative
  +
|-
  +
| ... || ...
  +
|-
  +
|}
  +
</div>
  +
; Transitive
  +
  +
* Imperfective participle: -taa, -tii, -te, -tii
  +
* Perfective participle: -aa, -ii, -e, -iim
  +
* Infinitive: -naa
  +
* Subjunctive: -uum, -e, -e, -em, -o, -em
  +
* Future: subjunctive + -gaa, -ge, -gii, -gii
  +
* Imperative:
  +
* Verbal adverbs: -kar / -0 kar
  +
  +
<pre>
  +
बोल; बोलना; inf.nom; vblex.tv
  +
बोल; बोलने; inf.obl; vblex.tv
  +
बोल; बोलता; impf.m.sg; vblex.tv
  +
बोल; बोलती; impf.f.sg; vblex.tv
  +
बोल; बोलते; impf.m.pl; vblex.tv
  +
बोल; बोलती; impf.f.pl; vblex.tv
  +
बोल; बोला; perf.m.sg; vblex.tv
  +
बोल; बोली; perf.f.sg; vblex.tv
  +
बोल; बोले; perf.m.pl; vblex.tv
  +
बोल; बोली; perf.f.pl; vblex.tv
  +
बोल; बोलूं; prs.p1.sg; vblex.tv
  +
बोल; बोले; prs.p2.sg; vblex.tv
  +
बोल; बोले; prs.p3.sg; vblex.tv
  +
बोल; बोलें; prs.p1.pl; vblex.tv
  +
बोल; बोलो; prs.p2.pl; vblex.tv
  +
बोल; बोलें; prs.p3.pl; vblex.tv
  +
बोल; बोलूंगा; fut.p1.m.sg; vblex.tv
  +
बोल; बोलेगा; fut.p2.m.sg; vblex.tv
  +
बोल; बोलेगा; fut.p3.m.sg; vblex.tv
  +
बोल; बोलेंगे; fut.p1.m.pl; vblex.tv
  +
बोल; बोलोगे; fut.p2.m.pl; vblex.tv
  +
बोल; बोलेंगे; fut.p3.m.pl; vblex.tv
  +
बोल; बोलूंगी; fut.p1.f.sg; vblex.tv
  +
बोल; बोलेगी; fut.p2.f.sg; vblex.tv
  +
बोल; बोलेगी; fut.p3.f.sg; vblex.tv
  +
बोल; बोलेंगी; fut.p1.f.pl; vblex.tv
  +
बोल; बोलोगी; fut.p2.f.pl; vblex.tv
  +
बोल; बोलेंगी; fut.p3.f.pl; vblex.tv
  +
बोल; बोल; imp.p2.sg; vblex.tv
  +
बोल; बोलो; imp.p2.pl; vblex.tv
  +
बोल; बोलिए; imp.p2.frm.pl; vblex.tv
  +
बोल; बोलकर; gna; vblex.tv
  +
बोल; बोलके; gna; vblex.tv
  +
बोल; बोलनेवाला; agnt.m.sg; vblex.tv
  +
बोल; बोलनेवाली; agnt.f.sg; vblex.tv
  +
बोल; बोलनेवाले; agnt.m.pl; vblex.tv
  +
बोल; बोलनेवाली; agnt.f.pl; vblex.tv
  +
</pre>
  +
  +
; Intransitive
   
 
===Verb patterns===
 
===Verb patterns===
  +
  +
; impf participle + "be" present
  +
  +
* pres
  +
  +
; stem + "raha" impf participle + "be" present
  +
  +
* "be" present + ger
  +
  +
; perf participle
  +
  +
* past
  +
  +
; perf participle + "be" present
  +
  +
* "have" present + pp
  +
  +
; perf participle + "be" past
  +
  +
* past
  +
* "have" past + pp
  +
  +
; impf participle + "be" past
  +
  +
* past
  +
* "used to" + inf
  +
  +
; impf participle + "raha" present + "be" past
  +
  +
* "be" past + ger
  +
  +
; future
  +
  +
* "will" present + inf
  +
  +
; impf participle + "raha" future
  +
  +
* "will be" + ger
  +
  +
; prs
  +
  +
* "may" present + inf
  +
  +
==Apertium Resources==
  +
*[https://github.com/apertium/apertium-hin apertium-hin]
  +
*[https://github.com/apertium/apertium-eng-hin apertium-eng-hin]
  +
*[https://github.com/apertium/apertium-mar-hin?files=1 apertium-mar-hin]
  +
*[https://github.com/apertium/apertium-urd-hin?files=1 apertium-urd-hin]
  +
  +
==External Resources==
  +
  +
===General===
  +
  +
* [http://www.aclweb.org/anthology/C10-2147 Urdu and Hindi: Translation and sharing of linguistic resources]
  +
* [http://www.cal.org/heritage/pdfs/voices-hindi-language.pdf Introduction to Hindi]
  +
* [https://www.researchgate.net/publication/313030658_Learning_of_Hindi_Phonology_as_a_Foreigner Learning of Hindi Phonology as a Foreigner]
  +
* [https://benjamins.com/catalog/loall.12 Hindi by Yamuna Kachru]
  +
  +
===Grammars===
  +
  +
* [http://www.koausa.org/iils/pdf/ModernHindiGrammar.pdf Modern Hindi Grammar, Omkar N. Koul]
  +
* [http://shodhganga.inflibnet.ac.in/bitstream/10603/78191/11/11_chapter%204.pdf Grammatical & Inflectional Analysis of Hindi and Dogri]
  +
* [https://surface.syr.edu/cgi/viewcontent.cgi?article=1170&context=suscholar The Oldest Grammar of Hindustani Tej K. Bhatia]
  +
* [http://esl.fis.edu/grammar/langdiff/hindi.htm Differences between Hindi and Urdu Grammar
  +
  +
  +
  +
  +
===Machine Translation===
  +
  +
* [http://web2py.iiit.ac.in/research_centres/publications/download/mastersthesis.pdf.af2224b7bc18088c.4b756e616c2d5468657369732d46696e616c2e706466.pdf Hindi to English Machine Translation, Kunal Sachdeva]
  +
  +
* [https://arxiv.org/ftp/arxiv/papers/1702/1702.01587.pdf A Hybrid Approach For Hindi-English Machine Translation]
  +
  +
* [https://airccj.org/CSCP/vol7/csit77206.pdf Experiments On Different Recurrent Neural Networks For English-Hindi Machine Translation]
  +
  +
* [https://www.cse.iitb.ac.in/~pb/papers/eng-hindi-mt.pdf Interlingua based English-Hindi Machine Translation and Language Divergence]
  +
  +
* [http://aircconline.com/ijaia/V8N5/8517ijaia04.pdf Building An Effective MT System For English-Hindi Using RNNs Ruchit Agrawal & Dipti Misra Sharma]
  +
  +
* [https://www.researchgate.net/publication/319351932_Neural_Machine_Translation_of_Indian_Languages Neural Machine Translation of Indian Languages]
  +
  +
* [https://www.hindawi.com/journals/tswj/2014/485737/ Quantum Neural Network Based Machine Translator for Hindi to English]
  +
  +
  +
  +
  +
====Languages Other than English====
  +
  +
* [http://h2p.learnpunjabi.org/ Hindi-Punjabi Machine Translation]
  +
* [http://www.academia.edu/3275646/A_Hybrid_Approach_for_Bengali_to_Hindi_Machine_Translation A Hybrid Approach for Bengali to Hindi Machine Translation, Sanjay Chatterji]
  +
  +
  +
===Morphology===
  +
  +
* [http://www.ijsrp.org/research-paper-0613/ijsrp-p18124.pdf Morphology: Indian Languages and European Languages (contains morphological information for both English and Hindi)]
  +
  +
* [http://web.stanford.edu/group/cslipublications/cslipublications/HPSG/2010/singh-sarma.pdf Hindi Noun Inflection and Distributed Morphology, Smriti Singh and Vaijayanthi M Sarma]
  +
  +
* [http://learnpunjabi.org/pdf/gslehal-pap21.pdf Hindi Morphological Analyzer and Generator]
  +
  +
* [http://aclweb.org/anthology/W12-2302 Hindi Derivational Morphological Analyzer]
  +
  +
  +
  +
===Dictionaries===
  +
  +
* http://hindi-english.org/
  +
* http://e-mahashabdkosh.rb-aai.in/
  +
* https://shabdkosh.raftaar.in/Hindi-English-Dictionary
  +
* http://www.aamboli.com/
  +
* [http://tdil-dc.in/index.php?option=com_download&task=showresourceDetails&toolid=1552&lang=en Bilingual Dictionary Marathi to Hindi]
  +
  +
====Multilingual====
  +
  +
* [http://troindia.in/journal/ijcesr/vol3isss9/74-80.pdf An English To Assamese, Bengali And Hindi Multilingual E-Dictionary]
  +
  +
  +
  +
===Corpora===
  +
  +
* [http://opus.nlpl.eu/ Hindi-English Parallel Corpora]
  +
* [http://www.lrec-conf.org/proceedings/lrec2014/pdf/835_Paper.pdf HindEnCorp – Hindi-English and Hindi-only Corpus for Machine Translation]
  +
* [https://arxiv.org/abs/1710.02855 The IIT Bombay English-Hindi Parallel Corpus]
  +
* [https://catalog.ldc.upenn.edu/LDC2008L02 Hindi WordNet]
  +
* [http://corpora.uni-leipzig.de/en?corpusId=hin_news_2011 Hindi News Corpus]
  +
  +
  +
   
 
==See also==
 
==See also==

Latest revision as of 11:17, 3 December 2018

English and Hindi for GSoC[edit]

English–Hindi is sometimes/often discouraged as a GSoC project because:

  1. it has been done unsuccessfully at least 3 times already;
  2. it's hard;
  3. Google already does it well (the GSoC project is "reaching state-of-the-art");
  4. ...

Todo list[edit]

Main article: /Work plan
  • Check that the story is correctly translated from English to Hindi and that there are no missing sentences.
  • Fix spelling errors in the story.
  • Add other personal pronouns on the model of 'I' -- in both the Hindi dictionary and the bilingual dictionary.
  • Come up with short example sentences (they should include a verb) for common postpositions "with the cat" "under the table". etc.
  • Every word in the bidix should have a POS tag
  • Every noun on the Hindi side should have gender.
  • Adjectives in English in the bidix should be marked for 'sint'.
  • Check if there are any forms missing from #Verb_conjugation

Disambiguation[edit]

^बच्चों/बच्चा<n><m><pl><obl>$ 
^की/का<post><f><sg><nom>/का<post><f><sg><obl>/का<post><f><pl><nom>/का<post><f><pl><obl>$ 
^मॉं/मॉं<n><f><sg><nom>/मॉं<n><f><sg><obl>$ 

Grammar stuff[edit]

Noun phrase[edit]

Postpositional phrase[edit]

 NP-obl post

Postposition can be simple or kā + adv/noun.

Genitive phrase[edit]


SN-obl kā-$GEN.$NBR.nom SN-$GEN.$NBR.nom

Verb conjugation[edit]

Tag Description
<impf> Imperfective participle
<perf> Perfective participle
<inf> Infinitive
<prs> Subjunctive
<fut> Future
<imp> Imperative
... ...
Transitive
  • Imperfective participle: -taa, -tii, -te, -tii
  • Perfective participle: -aa, -ii, -e, -iim
  • Infinitive: -naa
  • Subjunctive: -uum, -e, -e, -em, -o, -em
  • Future: subjunctive + -gaa, -ge, -gii, -gii
  • Imperative:
  • Verbal adverbs: -kar / -0 kar
बोल; बोलना; inf.nom; vblex.tv 
बोल; बोलने; inf.obl; vblex.tv 
बोल; बोलता; impf.m.sg; vblex.tv
बोल; बोलती; impf.f.sg; vblex.tv
बोल; बोलते; impf.m.pl; vblex.tv
बोल; बोलती; impf.f.pl; vblex.tv
बोल; बोला; perf.m.sg; vblex.tv
बोल; बोली; perf.f.sg; vblex.tv
बोल; बोले; perf.m.pl; vblex.tv
बोल; बोली; perf.f.pl; vblex.tv
बोल; बोलूं; prs.p1.sg; vblex.tv
बोल; बोले; prs.p2.sg; vblex.tv
बोल; बोले; prs.p3.sg; vblex.tv
बोल; बोलें; prs.p1.pl; vblex.tv
बोल; बोलो; prs.p2.pl; vblex.tv
बोल; बोलें; prs.p3.pl; vblex.tv
बोल; बोलूंगा; fut.p1.m.sg; vblex.tv
बोल; बोलेगा; fut.p2.m.sg; vblex.tv
बोल; बोलेगा; fut.p3.m.sg; vblex.tv
बोल; बोलेंगे; fut.p1.m.pl; vblex.tv
बोल; बोलोगे; fut.p2.m.pl; vblex.tv
बोल; बोलेंगे; fut.p3.m.pl; vblex.tv
बोल; बोलूंगी; fut.p1.f.sg; vblex.tv
बोल; बोलेगी; fut.p2.f.sg; vblex.tv
बोल; बोलेगी; fut.p3.f.sg; vblex.tv
बोल; बोलेंगी; fut.p1.f.pl; vblex.tv
बोल; बोलोगी; fut.p2.f.pl; vblex.tv
बोल; बोलेंगी; fut.p3.f.pl; vblex.tv
बोल; बोल; imp.p2.sg; vblex.tv
बोल; बोलो; imp.p2.pl; vblex.tv
बोल; बोलिए; imp.p2.frm.pl; vblex.tv
बोल; बोलकर; gna; vblex.tv
बोल; बोलके; gna; vblex.tv
बोल; बोलनेवाला; agnt.m.sg; vblex.tv
बोल; बोलनेवाली; agnt.f.sg; vblex.tv
बोल; बोलनेवाले; agnt.m.pl; vblex.tv
बोल; बोलनेवाली; agnt.f.pl; vblex.tv
Intransitive

Verb patterns[edit]

impf participle + "be" present
  • pres
stem + "raha" impf participle + "be" present
  • "be" present + ger
perf participle
  • past
perf participle + "be" present
  • "have" present + pp
perf participle + "be" past
  • past
  • "have" past + pp
impf participle + "be" past
  • past
  • "used to" + inf
impf participle + "raha" present + "be" past
  • "be" past + ger
future
  • "will" present + inf
impf participle + "raha" future
  • "will be" + ger
prs
  • "may" present + inf

Apertium Resources[edit]

External Resources[edit]

General[edit]

Grammars[edit]



Machine Translation[edit]



Languages Other than English[edit]


Morphology[edit]


Dictionaries[edit]

Multilingual[edit]


Corpora[edit]



See also[edit]