Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
csdn_franckjun
Paddle
提交
06cbd81e
P
Paddle
项目概览
csdn_franckjun
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
1
Issue
1
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
06cbd81e
编写于
3月 02, 2017
作者:
D
dangqingqing
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
CONLL05 dataset for SRL
上级
cdecd53b
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
188 addition
and
0 deletion
+188
-0
python/paddle/v2/dataset/conll05.py
python/paddle/v2/dataset/conll05.py
+188
-0
未找到文件。
python/paddle/v2/dataset/conll05.py
0 → 100644
浏览文件 @
06cbd81e
import
paddle.v2.dataset.common
import
tarfile
import
gzip
import
itertools
__all__
=
[
'test, get_dict'
,
'get_embedding'
]
"""
Conll 2005 dataset. Paddle semantic role labeling Book and demo use this
dataset as an example. Because Conll 2005 is not free in public, the default
downloaded URL is test set of Conll 2005 (which is public). Users can change
URL and MD5 to their Conll dataset.
"""
DATA_URL
=
'http://www.cs.upc.edu/~srlconll/conll05st-tests.tar.gz'
DATA_MD5
=
'387719152ae52d60422c016e92a742fc'
WORDDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/wordDict.txt'
WORDDICT_MD5
=
'ea7fb7d4c75cc6254716f0177a506baa'
VERBDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/verbDict.txt'
VERBDICT_MD5
=
'0d2977293bbb6cbefab5b0f97db1e77c'
TRGDICT_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/targetDict.txt'
TRGDICT_MD5
=
'd8c7f03ceb5fc2e5a0fa7503a4353751'
EMB_URL
=
'http://paddlepaddle.bj.bcebos.com/demo/srl_dict_and_embedding/emb'
EMB_MD5
=
'bf436eb0faa1f6f9103017f8be57cdb7'
UNK_IDX
=
0
def
load_dict
(
filename
):
d
=
dict
()
with
open
(
filename
,
'r'
)
as
f
:
for
i
,
line
in
enumerate
(
f
):
d
[
line
.
strip
()]
=
i
return
d
def
corpus_reader
(
data_path
,
words_name
,
props_name
):
"""
Read one corpus by corpus name. It returns an iterator. Each element of
this iterator is a tuple including sentence and labels. The sentence is
consist of a list of word IDs. The labels include a list of label IDs.
:param name: corpus name.
:type name: basestring
:return: a iterator of data.
:rtype: iterator
"""
def
reader
():
tf
=
tarfile
.
open
(
data_path
)
wf
=
tf
.
extractfile
(
words_name
)
pf
=
tf
.
extractfile
(
props_name
)
with
gzip
.
GzipFile
(
fileobj
=
wf
)
as
words_file
,
gzip
.
GzipFile
(
fileobj
=
pf
)
as
props_file
:
sentences
=
[]
labels
=
[]
one_seg
=
[]
for
word
,
label
in
itertools
.
izip
(
words_file
,
props_file
):
word
=
word
.
strip
()
label
=
label
.
strip
().
split
()
if
len
(
label
)
==
0
:
# end of sentence
for
i
in
xrange
(
len
(
one_seg
[
0
])):
a_kind_lable
=
[
x
[
i
]
for
x
in
one_seg
]
labels
.
append
(
a_kind_lable
)
if
len
(
labels
)
>=
1
:
verb_list
=
[]
for
x
in
labels
[
0
]:
if
x
!=
'-'
:
verb_list
.
append
(
x
)
for
i
,
lbl
in
enumerate
(
labels
[
1
:]):
cur_tag
=
'O'
is_in_bracket
=
False
lbl_seq
=
[]
verb_word
=
''
for
l
in
lbl
:
if
l
==
'*'
and
is_in_bracket
==
False
:
lbl_seq
.
append
(
'O'
)
elif
l
==
'*'
and
is_in_bracket
==
True
:
lbl_seq
.
append
(
'I-'
+
cur_tag
)
elif
l
==
'*)'
:
lbl_seq
.
append
(
'I-'
+
cur_tag
)
is_in_bracket
=
False
elif
l
.
find
(
'('
)
!=
-
1
and
l
.
find
(
')'
)
!=
-
1
:
cur_tag
=
l
[
1
:
l
.
find
(
'*'
)]
lbl_seq
.
append
(
'B-'
+
cur_tag
)
is_in_bracket
=
False
elif
l
.
find
(
'('
)
!=
-
1
and
l
.
find
(
')'
)
==
-
1
:
cur_tag
=
l
[
1
:
l
.
find
(
'*'
)]
lbl_seq
.
append
(
'B-'
+
cur_tag
)
is_in_bracket
=
True
else
:
print
'error:'
,
l
yield
sentences
,
verb_list
[
i
],
lbl_seq
sentences
=
[]
labels
=
[]
one_seg
=
[]
else
:
sentences
.
append
(
word
)
one_seg
.
append
(
label
)
return
reader
def
reader_creator
(
corpus_reader
,
word_dict
=
None
,
predicate_dict
=
None
,
label_dict
=
None
):
def
reader
():
for
sentence
,
predicate
,
labels
in
corpus_reader
():
sen_len
=
len
(
sentence
)
verb_index
=
labels
.
index
(
'B-V'
)
mark
=
[
0
]
*
len
(
labels
)
if
verb_index
>
0
:
mark
[
verb_index
-
1
]
=
1
ctx_n1
=
sentence
[
verb_index
-
1
]
else
:
ctx_n1
=
'bos'
if
verb_index
>
1
:
mark
[
verb_index
-
2
]
=
1
ctx_n2
=
sentence
[
verb_index
-
2
]
else
:
ctx_n2
=
'bos'
mark
[
verb_index
]
=
1
ctx_0
=
sentence
[
verb_index
]
if
verb_index
<
len
(
labels
)
-
1
:
mark
[
verb_index
+
1
]
=
1
ctx_p1
=
sentence
[
verb_index
+
1
]
else
:
ctx_p1
=
'eos'
if
verb_index
<
len
(
labels
)
-
2
:
mark
[
verb_index
+
2
]
=
1
ctx_p2
=
sentence
[
verb_index
+
2
]
else
:
ctx_p2
=
'eos'
word_idx
=
[
word_dict
.
get
(
w
,
UNK_IDX
)
for
w
in
sentence
]
pred_idx
=
[
predicate_dict
.
get
(
predicate
)]
*
sen_len
ctx_n2_idx
=
[
word_dict
.
get
(
ctx_n2
,
UNK_IDX
)]
*
sen_len
ctx_n1_idx
=
[
word_dict
.
get
(
ctx_n1
,
UNK_IDX
)]
*
sen_len
ctx_0_idx
=
[
word_dict
.
get
(
ctx_0
,
UNK_IDX
)]
*
sen_len
ctx_p1_idx
=
[
word_dict
.
get
(
ctx_p1
,
UNK_IDX
)]
*
sen_len
ctx_p2_idx
=
[
word_dict
.
get
(
ctx_p2
,
UNK_IDX
)]
*
sen_len
label_idx
=
[
label_dict
.
get
(
w
)
for
w
in
labels
]
yield
word_idx
,
pred_idx
,
ctx_n2_idx
,
ctx_n1_idx
,
\
ctx_0_idx
,
ctx_p1_idx
,
ctx_p2_idx
,
mark
,
label_idx
return
reader
()
def
get_dict
():
word_dict
=
load_dict
(
common
.
download
(
WORDDICT_URL
,
'conll05st'
,
WORDDICT_MD5
))
verb_dict
=
load_dict
(
common
.
download
(
VERBDICT_URL
,
'conll05st'
,
VERBDICT_MD5
))
label_dict
=
load_dict
(
common
.
download
(
TRGDICT_URL
,
'conll05st'
,
TRGDICT_MD5
))
return
word_dict
,
verb_dict
,
label_dict
def
get_embedding
():
return
common
.
download
(
EMB_URL
,
'conll05st'
,
EMB_MD5
)
def
test
():
word_dict
,
verb_dict
,
label_dict
=
get_dict
()
reader
=
corpus_reader
(
common
.
download
(
DATA_URL
,
'conll05st'
,
DATA_MD5
),
words_name
=
'conll05st-release/test.wsj/words/test.wsj.words.gz'
,
props_name
=
'conll05st-release/test.wsj/props/test.wsj.props.gz'
)
return
reader_creator
(
reader
,
word_dict
,
verb_dict
,
label_dict
)
if
__name__
==
'__main__'
:
print
get_embedding
()
for
f
in
test
():
print
f
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录