Joachim Bingel | 11d5b15 | 2014-02-11 21:33:47 +0000 | [diff] [blame] | 1 | bsp1.json: "Der Mann" |
| 2 | bsp2.json: "Der /+w1:3 Mann" |
| 3 | bsp3.json: "Der /+w1:3,s1 Mann" |
| 4 | bsp4.json: "(Der /+w1:3,s1 Mann) /+w5 geht" |
| 5 | bsp5.json: "(Der /+w1:3,s1 Mann) /-w5 geht" |
Joachim Bingel | 0207d5e | 2014-02-12 14:18:41 +0000 | [diff] [blame] | 6 | bsp6.json: "(Der /+w1:3,s1 Mann) /+w5 (geht weg)" |
| 7 | |
| 8 | cosmas1.json: "Buch" |
| 9 | cosmas2.json: "das Buch" // to demonstrate token sequences |
| 10 | cosmas3.json: "das /+w1:3 Buch" // word-distance constraint |
| 11 | cosmas4.json: "das /+w1:3,s1 Buch" // combined word-distance and sent-distance constraint |
| 12 | cosmas5.json: "(das /+w1:3,s1 Buch) /+w5 Tisch" // complex distance constraint on sequences |
| 13 | cosmas6.json: "(das /+w1:3,s1 Buch) /-w5 Tisch" // negative distance -> precedence |
| 14 | cosmas7.json: "(das /+w1:3,s1 Buch) /+w5 (auf dem Tisch)" |
| 15 | cosmas8.json: "Institut für Deutsche Sprache" // spelling variations: deutsche/Deutsche |
| 16 | cosmas9.json: "Institut für deutsche Sprache" |
| 17 | cosmas10.json: "Institut für $deutsche Sprache" // finds both |
| 18 | cosmas11.json: "Institut für &deutsch Sprache" // finds both if base form (lemma) is annotated |
| 19 | cosmas12.json: "Institut für /+w2 Sprache" // finds institutes for any language |
| 20 | cosmas13.json: "Institut für %+w1 deutsche Sprach e" // finds institutes for anything |
| 21 | cosmas14.json: "Institut für MORPH(A) Sprache" // finds institutes for any language |
| 22 | cosmas15.json: "wegen #IN(L) <s>" // finds 'wegen' at beginning of sentence |
| 23 | cosmas16.json: "$wegen #IN(L) <s>" // finds 'wegen' at beginning of sentence, also when capitalised |
| 24 | cosmas17.json: "#BED($wegen , +sa)" // equivalent to above |
| 25 | cosmas18.json: "#BEG(#ELEM(S))" // finds every sentence-initial word |
| 26 | cosmas19.json: "MORPH(V) #IN(L) #ELEM(S)" // e.g. questions |
| 27 | cosmas20.json: "MORPH(V) #IN(R) #ELEM(S)" // e.g. subordinate clauses |