Merge pull request #491 from LinguList/master

update data, fixes #479

CONTRIBUTORS.md

@@ -52,7 +52,8 @@ Anthony Grant | MS | 1.1
 Ben Yackley | P | 1.1
 Christoph Rzymski | CLPG | 1.1
 Claire Bowern | D | 1.1
-Cormac Anderson | C | 1.1
+Christoph Rzymski | CTLG | 1.2
+Cormac Anderson | CP | 1.1, 1.2
 Damian Satterthwaite-Phillips | D | 1.0 
 Doug Cooper | DCSM | 1.1
 Evgeniya Korovina | MSCLPA | 1.1
@@ -66,6 +67,7 @@ Lars Borin | DL | 1.0
 Magdalena Łuniewska | D | 1.1
 Martin Haspelmath | AD | 1.0  
 Maurizio Serva | MD | 1.1
+Mei-Shin Wu | CTLG | 1.2
 Michael Dunn | G | 1.1
 Nathan Hill | MSDP | 1.1
 Nicholas Evans | A | 1.0
@@ -75,7 +77,7 @@ Robert Blust | D | 1.0
 Sean Lee | D | 1.0
 Sebastian Nicolai | CMS | 1.0  
 Thiago Chacon | MSD | 1.0, 1.1 
-Tiago Tresoldi | CTLG | 1.1
+Tiago Tresoldi | CTLG | 1.1, 1.2
 Viola Kirchhoff da Cruz | CLS | 1.0 
 Wang Feng | D | 1.0
 Yunfan Lai | CTLG | 1.1

concepticondata/conceptlists.tsv

@@ -1,4 +1,5 @@
 ID	AUTHOR	YEAR	LIST_SUFFIX	ITEMS	TAGS	SOURCE_LANGUAGE	TARGET_LANGUAGE	URL	REFS	PDF	NOTE	PAGES	ALIAS
+Perrin-2010-110	Perrin, Loïc-Michel	2010		110	annotated	English,German,French	Global	https://journals.dartmouth.edu/cgi-bin/WebObjects/Journals.woa/xmlpage/1/article/353?htmlOnce=yes	Perrin2010	Perrin2010	This list was used as an initial questionnaire for colexification studies on a world-wide sample of languages.	276f	
 Sun-1991-1004	Sun, Hongkai et al.	1991		1004	questionnaire	English	Tibeto-Burman languages	http://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl	Sun1991		This concept list originally served as a questionnaire for a large-scale investigation on Tibeto-Burman languages. The original questionnaire was in Chinese with no English translation. Later the STEDT project (:bib:Matisoff2015) digitized the data, translating Chinese concept labels to English, but not listing the original Chinese forms. As a result, some concept labels are identical, although they are different in the Chinese version. We are still trying to add the original Chinese concept labels to this resource, but for the moment, we only link the STEDT version, occasionally adding Chinese concept labels, where we figure they are important to distinguish the original meaning.		
 Robinson-2012-398	Robinson, Laura C and Holton, Gary	2012		398	basic	English	Alor-Pantar languages	http://booksandjournals.brillonline.com/content/journals/10.1163/22105832-20120201	Robinson2012		The authors inform that the list is built upon the about 400 items of [Holton (2012)](:bib:Holton2012), but this source did not submit the dataset.		
 Heggarty-2017-200	Heggarty, Paul and Anderson, Cormac and Scarborough, Matthew	2017		200	basic	English	Indo-European languages	http://cobl.clld.org	Heggarty2017		This is the basic list of 200 items which were selected for the Cognates in Basic Lexicon project. The compilers selected the items following various different criteria, such as ease of elicitation, non-fuzziness of the meaning, representation in Indo-European languages, and more. The numbers are at times higher than 200. This results from the earlier selection which containted more concepts which were no longer used in the official version.		
@@ -221,5 +222,5 @@ Kibrik-2012-122	Kibrik, Andrej D.	2012		122	basic	English	Global		Kibrik2012		A
 Marrison-1967-917	Marrison, Geoffrey Edward	1967		917	basic,areal	English	Naga				A list of 917 lexical items of Ao Naga (Chungli). But the document only listed 911 items.		
 Kaiping-2018-591	Kaiping, Gereon A. AND Klamer, Marian	2018		591	basic,areal	English,Indonesian	Languages of eastern Indonesia	http://www.model-ling.eu/lexirumah/parameters	Kaiping2018		The LexiRumah list was specifically designed for the study of Austronesian and Timor-Alor-Pantar families, and their contact history, in eastern Indonesia. The list expands Swadesh's [200 item](:ref:Swadesh-1952-200) list by concepts which were found to be subject to frequent borrowing (cf. [Tadmor 2009)](:ref:Tadmor2009), as well as concepts of strong cultural importance in the area (eg. betel nut, lontar palm, ritual ground).		LexiRumah
 Marrison-1967-909	Marrison, Geoffrey Edward	1967		909	basic,areal	English	Naga	http://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl/gnis?lexicon.lgid=270	Marrison1967		A list of 909 lexical items of Ao Naga (Chungli).		
-Kolipakam-2018-100	Kolipakam, Vishnupriya and Jordan, Fiona M. and Dunn, Michael and Greenhill, Simon J. and Bouckaert, Remco and Gray, Russell D. and Verkerk, Annemarie	2018		100	basic,areal	English	Dravidian		Kolipakam2018	Kolipakam2018	A 100 item wordlist for Dravidian languages based on [Kassian et al's list](:ref:Kassian-2010-116)		
+Kolipakam-2018-100	Kolipakam, Vishnupriya and Jordan, Fiona M. and Dunn, Michael and Greenhill, Simon J. and Bouckaert, Remco and Gray, Russell D. and Verkerk, Annemarie	2018		100	basic,areal	English	Dravidian		Kolipakam2018		A 100 item wordlist for Dravidian languages based on [Kassian et al's list](:ref:Kassian-2010-116)		
 Reinhard-1970-337	Reinhard, Johan and Toba, Tim	1970		337	basic,areal	English	Kusunda		Reinhard1970		There are 337 items in the book.		

concepticondata/conceptlists/Perrin-2010-110.tsv

@@ -0,0 +1,111 @@
+ID	NUMBER	ENGLISH	FRENCH	GERMAN	CONCEPTICON_ID	CONCEPTICON_GLOSS	SIMILARITY
+Perrin-2010-110-1	1	ACID	acide	sauer	1906	SOUR
+Perrin-2010-110-2	2	BAD	mauvais	schlecht	1292	BAD
+Perrin-2010-110-3	3	BEAUTIFUL	beau	schön	1427	BEAUTIFUL
+Perrin-2010-110-4	4	BENT	courbé	krumm	297	CROOKED
+Perrin-2010-110-5	5	BIG	gros	groß	1202	BIG
+Perrin-2010-110-6	6	BITTER	amer	bitter	887	BITTER
+Perrin-2010-110-7	7	BLUNT	émoussé	stumpf	379	BLUNT
+Perrin-2010-110-8	8	BOILED	cuit	gekocht	269	COOKED
+Perrin-2010-110-9	9	BRAVE	courageux	mutig	3	BRAVE
+Perrin-2010-110-10	10	CALM	calme	ruhig	258	CALM
+Perrin-2010-110-11	11	CHEAP	bon-marché	billig	1887	CHEAP
+Perrin-2010-110-12	12	light	CLAIR. 	hell	679	BRIGHT
+Perrin-2010-110-13	13	CLEAN	propre	sauber	704	CLEAN
+Perrin-2010-110-14	14	CLEVER	malin	schlau	1310	CLEVER
+Perrin-2010-110-15	15	COLD	froid	kalt	1287	COLD
+Perrin-2010-110-16	16	CONSTANT	constant	beständig		
+Perrin-2010-110-17	17	COOL	frais	frisch	2483	COLD (OF WEATHER)
+Perrin-2010-110-18	18	COWARDLY	lâche	feige		
+Perrin-2010-110-19	19	DEEP	profond	tief	1593	DEEP
+Perrin-2010-110-20	20	DIFFICULT	difficile	schwierig	584	DIFFICULT
+Perrin-2010-110-21	21	DELICIOUS	délicieux	schmackhaft	1813	TASTY
+Perrin-2010-110-22	22	DENSE	dense	dicht	2239	DENSE
+Perrin-2010-110-23	23	thick	épais	DICK	1244	THICK
+Perrin-2010-110-24	24	thick	épais (non-liquide)	DICKFLÜSSIG	2239	DENSE
+Perrin-2010-110-25	25	DIRTY	sale	schmutzig	1230	DIRTY
+Perrin-2010-110-26	26	soft	DOUX	sanft	1856	SOFT
+Perrin-2010-110-27	27	DRESSED	habillé	angezogen		
+Perrin-2010-110-28	28	right	DROITE	rechts	1019	RIGHT
+Perrin-2010-110-29	29	DRY	sec	trocken	1398	DRY
+Perrin-2010-110-30	30	EASY	facile	einfach	686	EASY
+Perrin-2010-110-31	31	EMPTY	vide	leer	1624	EMPTY
+Perrin-2010-110-32	32	EXPENSIVE	cher	teuer	1426	EXPENSIVE
+Perrin-2010-110-33	33	FAR	loin	fern	1406	FAR
+Perrin-2010-110-34	34	FAST	rapide	schnell	1631	FAST
+Perrin-2010-110-35	35	FAT	gras	fett	1279	FAT (OBESE)
+Perrin-2010-110-36	36	FEARFUL	peureux	ängstlich	528	DREADFUL
+Perrin-2010-110-37	37	FLAT	plat	flach	1633	FLAT
+Perrin-2010-110-38	38	FRAGILE	fragile	zerbrechlich		
+Perrin-2010-110-39	39	FREQUENT	fréquent	häufig		
+Perrin-2010-110-40	40	FULL	plein	voll	1429	FULL
+Perrin-2010-110-41	41	GAY	joyeux	fröhlich	1495	HAPPY
+Perrin-2010-110-42	42	GENEROUS	généreux	freigiebig		
+Perrin-2010-110-43	43	HEALTHY	en bonne santé	gesund	1364	HEALTHY
+Perrin-2010-110-44	44	GOOD	bon	gut	1035	GOOD
+Perrin-2010-110-45	45	HANDICAPPED	infirme	behindert		
+Perrin-2010-110-46	46	HARD	dur	hart	1884	HARD
+Perrin-2010-110-47	47	HEAVY	lourd	schwer	1210	HEAVY
+Perrin-2010-110-48	48	HOT	chaud (brûlant)	heiß	1286	HOT
+Perrin-2010-110-49	49	FOOLISH	idiot	dumm	1518	STUPID
+Perrin-2010-110-50	50	ILL	malade	krank	1847	SICK
+Perrin-2010-110-51	51	LARGE	grand, vaste	groß	1202	BIG
+Perrin-2010-110-52	52	LAZY	paresseux	faul	1564	LAZY
+Perrin-2010-110-53	53	LIGHT	léger	leicht	1052	LIGHT (WEIGHT)
+Perrin-2010-110-54	54	NOT DENSE	espacé	licht(er).		
+Perrin-2010-110-55	55	TIED UP	lié	festgebunden		
+Perrin-2010-110-56	56	LIMPING	boiteux	hinkend		
+Perrin-2010-110-57	57	LITTLE	petit, jeune	klein	1246	SMALL
+Perrin-2010-110-58	58	LONG	long	lang	1203	LONG
+Perrin-2010-110-59	59	untied	détaché	LOSE	2506	LOOSE
+Perrin-2010-110-60	60	LOUD	bruyant	laut	377	LOUD
+Perrin-2010-110-61	61	thin	MAIGRE	mager	2219	LEAN (MEAT)
+Perrin-2010-110-62	62	soft	MOU	weich	1856	SOFT
+Perrin-2010-110-63	63	NASTY	méchant	boshaft	419	SEVERE
+Perrin-2010-110-64	64	NARROW	étroit	eng	1267	NARROW
+Perrin-2010-110-65	65	NEAR	proche	nah	1942	NEAR
+Perrin-2010-110-66	66	NEW	nouveau	neu	1231	NEW
+Perrin-2010-110-67	67	NUMEROUS	nombreux	zahlreich	1198	MANY
+Perrin-2010-110-68	68	OLD	vieux	alt	1229	OLD
+Perrin-2010-110-69	69	OPEN	ouvert	offen	1156	OPEN
+Perrin-2010-110-70	70	PAINFUL	douloureux	schmerzhaft	1129	PAINFUL
+Perrin-2010-110-71	71	POOR	pauvre	arm	1674	POOR
+Perrin-2010-110-72	72	POLITE	poli	höflich	583	KIND OR POLITE
+Perrin-2010-110-73	73	PROUD	fier	stolz	174	PROUD
+Perrin-2010-110-74	74	PURE	pur	rein	1147	PURE
+Perrin-2010-110-75	75	RAW	cru	roh	1959	RAW
+Perrin-2010-110-76	76	RIPE	mûr	reif	178	RIPE
+Perrin-2010-110-77	77	ROTTEN	pourri	verdorben	1728	ROTTEN
+Perrin-2010-110-78	78	ROUGH	rugueux	rauh	1923	ROUGH
+Perrin-2010-110-79	79	ROUND	rond	rund	1395	ROUND
+Perrin-2010-110-80	80	RUDE	impoli	unhöflich	1412	RUDE
+Perrin-2010-110-81	81	SHALLOW	peu profond	seicht	193	SHALLOW
+Perrin-2010-110-82	82	SALT	salé	salzig	1274	SALT
+Perrin-2010-110-83	83	SHARP	tranchant	scharf	1396	SHARP
+Perrin-2010-110-84	84	SHORT	court	kurz	1645	SHORT
+Perrin-2010-110-85	85	SHY	timide	schüchtern	487	SHY
+Perrin-2010-110-86	86	SILENT	silencieux	still	48	BE SILENT
+Perrin-2010-110-87	87	SLOW	lent	langsam	701	SLOW
+Perrin-2010-110-88	88	SMALL	petit (de taille)	klein	1246	SMALL
+Perrin-2010-110-89	89	SMOOTH	lisse	glatt	1234	SMOOTH
+Perrin-2010-110-90	90	SOLID	solide	fest	3003	SOLID
+Perrin-2010-110-91	91	SOUR	aigre	sauer	1906	SOUR
+Perrin-2010-110-92	92	pointed	pointu	SPITZ	372	POINTED
+Perrin-2010-110-93	93	STINGY	avare	geizig	1774	STINGY
+Perrin-2010-110-94	94	STINKY	malodorant	stinkend	42	STINKING
+Perrin-2010-110-95	95	STRAIGHT	droit	gerade	1404	STRAIGHT
+Perrin-2010-110-96	96	STRONG	fort	stark	785	STRONG
+Perrin-2010-110-97	97	STUBBORN	têtu	stur		
+Perrin-2010-110-98	98	SUPERFICIAL	superficiel	oberflächlich		
+Perrin-2010-110-99	99	SWEET	sucré	süß	717	SWEET
+Perrin-2010-110-100	100	TIGHT	serré	eng	3053	TIGHT
+Perrin-2010-110-101	101	THIN	mince	dünn	1400	THIN (SLIM)
+Perrin-2010-110-102	102	TRUE	vrai	wahr	1657	TRUE
+Perrin-2010-110-103	103	WARM	chaud	warm	1232	WARM
+Perrin-2010-110-104	104	WEAK	faible	schwach	1601	WEAK
+Perrin-2010-110-105	105	WET	humide	feucht	1726	WET
+Perrin-2010-110-106	106	WHITE	blanc	weiß	1335	WHITE
+Perrin-2010-110-107	107	WIDE	large	weit	1243	WIDE
+Perrin-2010-110-108	108	WISE	sage	weise	698	WISE
+Perrin-2010-110-109	109	WRONG	faux	falsch	1390	WRONG
+Perrin-2010-110-110	110	YOUNG	jeune	jung	1207	YOUNG

concepticondata/conceptlists/README.md

@@ -99,7 +99,7 @@
 | [Kibrik-2012-122](Kibrik-2012-122.tsv) | 103 | 84 | 0 |
 | [Kingsada-1999-303](Kingsada-1999-303.tsv) | 297 | 98 | 1 |
 | [Kitchen-2009-95](Kitchen-2009-95.tsv) | 95 | 100 | 0 |
-| [Kolipakam-2018-100](Kolipakam-2018-100.tsv) | 0 | 0 | 0 |
+| [Kolipakam-2018-100](Kolipakam-2018-100.tsv) | 100 | 100 | 0 |
 | [Kraft-1981-434](Kraft-1981-434.tsv) | 434 | 100 | 6 |
 | [Krisadawan-2000-210](Krisadawan-2000-210.tsv) | 211 | 100 | 1 |
 | [Larson-1972-68](Larson-1972-68.tsv) | 66 | 100 | 0 |
@@ -150,6 +150,7 @@
 | [Pallas-1789-285](Pallas-1789-285.tsv) | 282 | 98 | 10 |
 | [Payne-1991-202](Payne-1991-202.tsv) | 202 | 100 | 39 |
 | [Peiros-1999-100](Peiros-1999-100.tsv) | 100 | 100 | 0 |
+| [Perrin-2010-110](Perrin-2010-110.tsv) | 98 | 89 | 5 |
 | [Peust-2013-54](Peust-2013-54.tsv) | 54 | 100 | 0 |
 | [Pozdniakov-2014-100a](Pozdniakov-2014-100a.tsv) | 100 | 100 | 0 |
 | [Pozdniakov-2014-100b](Pozdniakov-2014-100b.tsv) | 100 | 100 | 0 |
@@ -158,7 +159,7 @@
 | [Reinhard-1970-337](Reinhard-1970-337.tsv) | 295 | 87 | 27 |
 | [Ringe-1992-100](Ringe-1992-100.tsv) | 100 | 100 | 0 |
 | [Ringe-2002-333](Ringe-2002-333.tsv) | 333 | 100 | 0 |
-| [Robinson-2012-398](Robinson-2012-398.tsv) | 386 | 96 | 0 |
+| [Robinson-2012-398](Robinson-2012-398.tsv) | 393 | 98 | 0 |
 | [SIL-1980-281](SIL-1980-281.tsv) | 282 | 100 | 1 |
 | [SIL-2002-436](SIL-2002-436.tsv) | 442 | 100 | 5 |
 | [Samarin-1967-100](Samarin-1967-100.tsv) | 100 | 100 | 0 |
@@ -227,5 +228,5 @@
 | [Zorc-1974-100](Zorc-1974-100.tsv) | 100 | 100 | 0 |
 | [vanderWouw-1974-28](vanderWouw-1974-28.tsv) | 28 | 100 | 0 |
 
-(224 rows)
+(225 rows)
 

concepticondata/references/references.bib

@@ -1,6 +1,17 @@
 % This file was created with JabRef 2.10.
 % Encoding: UTF8
 
+@Article{Perrin2010,
+  Title                               = {{P}olysemous qualities and universal networks, invariance and diversity},
+  Author                              = {Perrin, Loïc-Michel},
+  Journal                             = {Linguistic Discovery},
+  Number                              = {1},
+  Pages                               = {259-280},
+  Volume                              = {8},
+  Year                                = {2010},
+}
+
+
 @inproceedings{List2016a,
   Publisher                           = {European Language Resources Association (ELRA)},
   Author                              = {List, Johann-Mattis and Cysouw, Michael and Forkel, Robert},

pyconcepticon/data/map-af.tsv

@@ -260,5 +260,5 @@ ID	GLOSS	PRIORITY
 55	WHISPER///fluister	1
 3107	WHISTLE (INSTRUMENT)///fluitjie	1
 1025	WHISTLE///blaas	1
-958	WILD ANIMAL////Az/	1
+958	WILD ANIMAL////\A\z/	1
 1672	WRITE///skryf	1