From 46250f60acdcdb847780789ed3a715639c67c9fa Mon Sep 17 00:00:00 2001 From: adrianeboyd Date: Sat, 23 Nov 2019 14:57:21 +0100 Subject: [PATCH] Add missing tags to el/es/pt tag maps (#4696) * Add missing tags to pt tag map * Add missing tags to es tag map * Add missing tags to el tag map * Add missing symbol in el tag map --- spacy/lang/el/tag_map.py | 18 +++++++++++++++++- spacy/lang/es/tag_map.py | 3 +++ spacy/lang/pt/tag_map.py | 14 ++++++++++++++ 3 files changed, 34 insertions(+), 1 deletion(-) diff --git a/spacy/lang/el/tag_map.py b/spacy/lang/el/tag_map.py index 073849c23..30816dbe4 100644 --- a/spacy/lang/el/tag_map.py +++ b/spacy/lang/el/tag_map.py @@ -2,7 +2,7 @@ from __future__ import unicode_literals from ...symbols import POS, PUNCT, SYM, ADJ, CCONJ, SCONJ, NUM, DET, ADV, ADP, X, VERB -from ...symbols import NOUN, PROPN, PART, INTJ, PRON +from ...symbols import NOUN, PROPN, PART, INTJ, PRON, AUX TAG_MAP = { @@ -4249,4 +4249,20 @@ TAG_MAP = { "Voice": "Act", "Case": "Nom|Gen|Dat|Acc|Voc", }, + 'ADJ': {POS: ADJ}, + 'ADP': {POS: ADP}, + 'ADV': {POS: ADV}, + 'AtDf': {POS: DET}, + 'AUX': {POS: AUX}, + 'CCONJ': {POS: CCONJ}, + 'DET': {POS: DET}, + 'NOUN': {POS: NOUN}, + 'NUM': {POS: NUM}, + 'PART': {POS: PART}, + 'PRON': {POS: PRON}, + 'PROPN': {POS: PROPN}, + 'SCONJ': {POS: SCONJ}, + 'SYM': {POS: SYM}, + 'VERB': {POS: VERB}, + 'X': {POS: X}, } diff --git a/spacy/lang/es/tag_map.py b/spacy/lang/es/tag_map.py index e6b93e318..7a7c9d549 100644 --- a/spacy/lang/es/tag_map.py +++ b/spacy/lang/es/tag_map.py @@ -305,6 +305,9 @@ TAG_MAP = { "VERB__VerbForm=Ger": {"morph": "VerbForm=Ger", POS: VERB}, "VERB__VerbForm=Inf": {"morph": "VerbForm=Inf", POS: VERB}, "X___": {"morph": "_", POS: X}, + "___PunctType=Quot": {POS: PUNCT}, + "___VerbForm=Inf": {POS: VERB}, + "___Number=Sing|Person=2|PronType=Prs": {POS: PRON}, "_SP": {"morph": "_", POS: SPACE}, } # fmt: on diff --git a/spacy/lang/pt/tag_map.py b/spacy/lang/pt/tag_map.py index 51c2b20b5..cdc7de57e 100644 --- a/spacy/lang/pt/tag_map.py +++ b/spacy/lang/pt/tag_map.py @@ -5039,5 +5039,19 @@ TAG_MAP = { "punc": {POS: PUNCT}, "v-pcp|M|P": {POS: VERB}, "v-pcp|M|S": {POS: VERB}, + "ADJ": {POS: ADJ}, + "AUX": {POS: AUX}, + "CCONJ": {POS: CCONJ}, + "DET": {POS: DET}, + "INTJ": {POS: INTJ}, + "NUM": {POS: NUM}, + "PART": {POS: PART}, + "PRON": {POS: PRON}, + "PUNCT": {POS: PUNCT}, + "SCONJ": {POS: SCONJ}, + "SYM": {POS: SYM}, + "VERB": {POS: VERB}, + "X": {POS: X}, + "adv": {POS: ADV}, "_SP": {POS: SPACE}, }