Dravidian languages

The Dravidian languages (dra) constitute a language family of about 70 languages spoken primarily in South Asia. The four most populous Dravidian languages, Telugu, Tamil, Kannada, and Malayalam, are recognized by the Constitution of India and encompass a significant portion of the over 215 million Dravidian speakers.

The master plan involves generating independent finite-state transducers for each language, and then making individual dictionaries and transfer rules for every pair. The current status of these goals is listed below.

Status

The ultimate goal is to have multi-purposable transducers for a variety of Dravidian languages. These can then be paired for X→Y translation with the addition of a CG for language X and transfer rules / dictionary for the pair X→Y. Below is listed development progress for each language's transducers and dictionary pairs.

Transducers

Once a transducer has ~80% coverage on a range of medium-large corpora we can say it is "working". Over 90% and it can be considered to be "production".

name	language	native name	ISO 639		formalism	state	stems	paradigms	coverage	location	primary authors
			-2	-3
apertium-mal	Malayalam	മലയാളം	ml	mal	HFST (lexc+twol)	prototype	14313	-		apertium-mal (incubator)	Tachyons, Francis Tyers
apertium-tel	Telugu	తెలుగు	te	tel	lttoolbox	prototype				apertium-tel (incubator)	kvsprasad

Existing language pairs

Text in italics denotes language pairs in the incubator. Regular text denotes a developing language pair in staging, while text in bold denotes a stable well-working language pair in trunk and text in bold and italics denotes a pair in staging. Bidix stems as counted with dixcounter are displayed below.

	tel	mal
tel	-
mal		-
eng	eng-tel 1	mal-eng 9,095

Dravidian languages by subgroup

The Dravidian languages form a close-knit family. Most scholars agree on four groups: North, Central (Kolami–Parji), South-Central (Telugu–Kui) and South Dravidian:

• Central (Kolami–Parji) languages
  • Kolami-Naiki languages (Kolami)
  • Parji-Gadaba languages (Duruwa, Gadaba)
• Northern languages (Brahui, Kurux, Sauria)
• Southern (Tamil–Tulu) languages
  • Tamil-Kannada (Tamil, Malayalam, Kannada)
  • Tulu languages (Tulu, Koraga, Kudiya)
• South-Central (Telugu-Kui) languages
  • Gondi-Kui languages (Gondi, Konda-Kui)
  • Telugu languages (Telugu, Savara, Chenchu)

Samples

Article 1 of the Universal Declaration of Human Rights:

All human beings are born free and equal in dignity and rights. They are endowed with reason and conscience and should act towards one another in a spirit of brotherhood.

Language	Text
Kannada	ಎಲ್ಲಾ ಮಾನವರೂ ಸ್ವತಂತ್ರರಾಗಿಯೇ ಜನಿಸಿದ್ಧಾರೆ. ಹಾಗೂ ಘನತೆ ಮತ್ತು ಹಕ್ಕುಗಳಲ್ಲಿ ಸಮಾನರಾಗಿದ್ದಾರೆ. ವಿವೇಕ ಮತ್ತು ಅಂತಃಕರಣ ಗಳನ್ನು ಪದೆದವರಾದ್ದ ರಿಂದ ಅವರು ಪರಸ್ಪರ ಸಹೋದರ ಭಾವದಿಂದ ವರ್ತಿಸಚೀಕು.
Malayalam	മനുഷ്യരെല്ലാവരും തുല്യാവകാശങ്ങളോടും അന്തസ്സോടും സ്വാതന്ത്ര്യത്തോടുംകൂടി ജനിച്ചിട്ടുള്ളവരാണ്‌. അന്യോന്യം ഭ്രാതൃഭാവത്തോടെ പെരുമാറുവാനാണ്‌ മനുഷ്യന്നു വിവേകബുദ്ധിയും മനസ്സാക്ഷിയും സിദ്ധമായിരിക്കുന്നത്‌.
Tamil	மனிதப் பிறிவியினர் சகலரும் சுதந்திரமாகவே பிறக்கின்றனர் ; அவர்கள் மதிப்பிலும், உரிமைகளிலும் சமமானவர்கள், அவர்கள் நியாயத்தையும் மனச்சாட்சியையும் இயற்பண்பாகப் பெற்றவர்கள். அவர்கள் ஒருவருடனொருவர் சகோதர உணர்வுப் பாங்கில் நடந்துகொள்ளல் வேண்டும்.

Vulnerability

This table summarizes the vulnerability of various Dravidian languages. Data is derived from the ‘Atlas of the World’s Languages in Danger, © UNESCO, http://www.unesco.org/culture/languages-atlas’ and Ethnologue.

Language	ISO639-3	Location	Speakers	Status
				Ethnologue	UNESCO
Nagarchal	nbg	India	0	10 (Extinct)	-
Urali	url	India	6,440	9 (Dormant)	-
Ullatan	ull	India	16,700	9 (Dormant)	-
Malaryan	mjq	India	35,000	9 (Dormant)	-
Bellari	brw	India	1,000	7 (Shifting)	4 (Critically endangered)
Manna-Dora	mju	India	30,000	7 (Shifting)	-
Bazigar	bfr	India	58,200	7 (Shifting)	-
Vishavan	vis	India	150	6b (Threatened)	-
Aranadan	aaf	India	200	6b (Threatened)	-
Allar	all	India	350	6b (Threatened)	-
Kadar	kej	India	1,960	6b (Threatened)	-
Thachanadan	thn	India	3,000	6b (Threatened)	-
Mannan	mjv	India	7,850	6b (Threatened)	-
Kumbaran	wkb	India	10,000	6b (Threatened)	-
Malavedan	mjr	India	12,600	6b (Threatened)	-
Koraga, Korra	kfd	India	14,000	6b (Threatened)	4 (Critically endangered)
Kurux, Nepali	kxl	Nepal	28,600	6b (Threatened)	-
Kurichiya	kfh	India	29,400	6b (Threatened)	-
Pardhan	pch	India	135,000	6b (Threatened)	-
Kui	kxu	India	916,000	6b (Threatened)	1 (Vulnerable)
Koraga, Mudu	vmd	India	-	6b (Threatened)	-
Holiya	hoy	India	500	6a (Vigorous)	-
Kalanadi	wkl	India	750	6a (Vigorous)	-
Kunduvadi	wku	India	1,000	6a (Vigorous)	-
Pathiya	pty	India	1,000	6a (Vigorous)	-
Mala Malasar	ima	India	1,000	6a (Vigorous)	-
Toda	tcx	India	1,560	6a (Vigorous)	4 (Critically endangered)
Kurumba, Alu	xua	India	2,500	6a (Vigorous)	-
Kudiya	kfg	India	2,800	6a (Vigorous)	-
Manda	mha	India	4,040	6a (Vigorous)	4 (Critically endangered)
Eravallan	era	India	5,000	6a (Vigorous)	-
Malapandaram	mjp	India	5,850	6a (Vigorous)	-
Malasar	ymr	India	7,760	6a (Vigorous)	-
Paliyan	pcf	India	9,520	6a (Vigorous)	-
Kolami, Southeastern	nit	India	10,000	6a (Vigorous)	4 (Critically endangered)
Kumarbhag Paharia	kmj	India	12,500	6a (Vigorous)	2 (Definitely endangered)
Gadaba, Pottangi Ollar	gdb	India	15,000	6a (Vigorous)	-
Malankuravan	mjo	India	18,600	6a (Vigorous)	-
Kanikkaran	kev	India	19,000	6a (Vigorous)	-
Kaikadi	kep	India	23,700	6a (Vigorous)	-
Sholaga	sle	India	24,000	6a (Vigorous)	-
Chenchu	cde	India	26,000	6a (Vigorous)	-
Kurumba, Mullu	kpb	India	26,000	6a (Vigorous)	-
Mukha-Dora	mmk	India	29,700	6a (Vigorous)	-
Khirwar	kwx	India	34,300	6a (Vigorous)	-
Kamar	keq	India	40,000	6a (Vigorous)	-
Duruwa	pci	India	51,200	6a (Vigorous)	4 (Critically endangered)
Maria	mrr	India	165,000	6a (Vigorous)	-
Waddar	wbq	India	172,000	6a (Vigorous)	-
Bharia	bha	India	197,000	6a (Vigorous)	-
Maria, Dandami	daq	India	200,000	6a (Vigorous)	-
Muria, Eastern	emu	India	200,000	6a (Vigorous)	-
Savara	svr	India	253,000	6a (Vigorous)	-
Pengo	peg	India	350,000	6a (Vigorous)	4 (Critically endangered)
Muria, Far Western	fmu	India	400,000	6a (Vigorous)	-
Muria, Western	mut	India	400,000	6a (Vigorous)	-
Kota	kfe	India	930	5 (Developing)	4 (Critically endangered)
Kurumba, Attapady	pkr	India	1,370	5 (Developing)	-
Muduga	udg	India	3,370	5 (Developing)	-
Chetti, Wayanad	ctt	India	5,000	5 (Developing)	-
Gadaba, Mudhili	gau	India	8,000	5 (Developing)	-
Muthuvan	muv	India	16,800	5 (Developing)	-
Konda-Dora	kfc	India	20,000	5 (Developing)	2 (Definitely endangered)
Ravula	yea	India	26,900	5 (Developing)	-
Kurumba, Betta	xub	India	32,000	5 (Developing)	-
Kurumba, Jennu	xuj	India	35,000	5 (Developing)	-
Sauria Paharia	mjt	India	61,000	5 (Developing)	-
Yerukula	yeu	India	69,500	5 (Developing)	2 (Definitely endangered)
Paniya	pcg	India	94,000	5 (Developing)	-
Gondi, Southern	ggo	India	100,000	5 (Developing)	-
Kolami, Northwestern	kfb	India	122,000	5 (Developing)	2 (Definitely endangered)
Badaga	bfq	India	135,000	5 (Developing)	2 (Definitely endangered)
Kuvi	kxv	India	158,000	5 (Developing)	2 (Definitely endangered)
Kurumba, Kannada	kfi	India	180,000	5 (Developing)	4 (Critically endangered)
Kodava	kfa	India	200,000	5 (Developing)	2 (Definitely endangered)
Irula	iru	India	200,000	5 (Developing)	1 (Vulnerable)
Koya	kff	India	362,000	5 (Developing)	-
Tulu	tcy	India	1,720,000	5 (Developing)	1 (Vulnerable)
Kurux	kru	India & Bangladesh	1,944,200	5 (Developing)	1 (Vulnerable)
Gondi, Northern	gno	India	1,950,000	5 (Developing)	-
Brahui	brh	Iran, Pakistan, Afghanistan	4,220,000	5 (Developing)	1 (Vulnerable)
Malayalam	mal	India	33,534,600	2 (Provincial)	-
Kannada	kan	India	37,739,040	2 (Provincial)	-
Tamil	tam	India	68,763,360	2 (Provincial)	-
Telugu	tel	India	74,049,000	2 (Provincial)	-

This article uses material from the Wikipedia article "Dravidian languages", which is released under the Creative Commons Attribution-Share-Alike License 3.0.