explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-30 09:53:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Supplemented with capitalized Swedish exceptions

Browse Source
This commit is contained in:
Magnus Burton 2017-01-10 16:07:20 +01:00 committed by GitHub
parent 56e2219b65
commit aad23ab0b4
1 changed files with 57 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
spacy/sv/tokenizer_exceptions.py
View File

@ -63,6 +63,63 @@ TOKENIZER_EXCEPTIONS = {
"sön.": [ "sön.": [
{ORTH: "sön.", LEMMA: "söndag"} {ORTH: "sön.", LEMMA: "söndag"}
], ],
"Jan.": [
{ORTH: "Jan.", LEMMA: "Januari"}
],
"Febr.": [
{ORTH: "Febr.", LEMMA: "Februari"}
],
"Feb.": [
{ORTH: "Feb.", LEMMA: "Februari"}
],
"Apr.": [
{ORTH: "Apr.", LEMMA: "April"}
],
"Jun.": [
{ORTH: "Jun.", LEMMA: "Juni"}
],
"Jul.": [
{ORTH: "Jul.", LEMMA: "Juli"}
],
"Aug.": [
{ORTH: "Aug.", LEMMA: "Augusti"}
],
"Sept.": [
{ORTH: "Sept.", LEMMA: "September"}
],
"Sep.": [
{ORTH: "Sep.", LEMMA: "September"}
],
"Okt.": [
{ORTH: "Okt.", LEMMA: "Oktober"}
],
"Nov.": [
{ORTH: "Nov.", LEMMA: "November"}
],
"Dec.": [
{ORTH: "Dec.", LEMMA: "December"}
],
"Mån.": [
{ORTH: "Mån.", LEMMA: "Måndag"}
],
"Tis.": [
{ORTH: "Tis.", LEMMA: "Tisdag"}
],
"Ons.": [
{ORTH: "Ons.", LEMMA: "Onsdag"}
],
"Tors.": [
{ORTH: "Tors.", LEMMA: "Torsdag"}
],
"Fre.": [
{ORTH: "Fre.", LEMMA: "Fredag"}
],
"Lör.": [
{ORTH: "Lör.", LEMMA: "Lördag"}
],
"Sön.": [
{ORTH: "Sön.", LEMMA: "Söndag"}
],
"sthlm": [ "sthlm": [
{ORTH: "sthlm", LEMMA: "Stockholm"} {ORTH: "sthlm", LEMMA: "Stockholm"}
], ],