From 07ffff19ad790c8c9a52e27b815320e781cc9eab Mon Sep 17 00:00:00 2001
From: Mateusz Klimaszewski <mk.klimaszewski@gmail.com>
Date: Wed, 23 Sep 2020 10:30:02 +0200
Subject: [PATCH] Fix adding enhanced labels.
---
combo/data/dataset.py | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/combo/data/dataset.py b/combo/data/dataset.py
index 0b53df3..2877a65 100644
--- a/combo/data/dataset.py
+++ b/combo/data/dataset.py
@@ -124,7 +124,7 @@ class UniversalDependenciesDatasetReader(allen_data.DatasetReader):
enhanced_deprels.append(deprels[idx])
t_deps = t["deps"]
if t_deps and t_deps != "_":
- t_heads, t_deprels = zip(*[tuple(d.split(":")) for d in t_deps.split("|")])
+ t_deprels, t_heads = zip(*t_deps)
enhanced_heads.extend([(idx, t) for t in t_heads])
enhanced_deprels.extend(t_deprels)
fields_["enhanced_heads"] = allen_fields.AdjacencyField(
@@ -137,7 +137,8 @@ class UniversalDependenciesDatasetReader(allen_data.DatasetReader):
indices=enhanced_heads,
sequence_field=text_field,
labels=enhanced_deprels,
- label_namespace="enhanced_deprels_labels",
+ # Label namespace should match regular tree parsing.
+ label_namespace="deprel_labels",
padding_value=0,
)
else:
--
GitLab