File size: 11,499 Bytes
ac6c40f
 
57616af
ac6c40f
d1a58c9
 
 
 
 
 
 
 
 
 
ef1f338
d1a58c9
 
 
 
 
57616af
 
 
 
 
 
 
 
 
d1a58c9
 
 
 
 
ac6c40f
57616af
ac6c40f
57616af
 
 
d1a58c9
 
57616af
 
 
d1a58c9
 
 
57616af
d1a58c9
 
 
 
57616af
d1a58c9
 
 
 
 
 
 
 
 
 
57616af
d1a58c9
 
 
57616af
 
 
d1a58c9
 
57616af
13fd677
 
 
 
 
57616af
 
d1a58c9
 
 
13fd677
57616af
 
d1a58c9
 
 
57616af
 
13fd677
 
 
57616af
 
 
 
d1a58c9
 
 
57616af
d1a58c9
 
 
57616af
d1a58c9
 
 
 
57616af
d1a58c9
 
 
 
57616af
 
 
 
 
 
 
 
d1a58c9
 
 
57616af
 
d1a58c9
 
 
57616af
d1a58c9
 
 
 
57616af
 
d1a58c9
 
 
 
57616af
d1a58c9
 
 
57616af
 
d1a58c9
ef1f338
d1a58c9
 
57616af
 
 
ef1f338
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1a58c9
 
57616af
 
 
d1a58c9
 
57616af
 
 
d1a58c9
 
57616af
 
 
d1a58c9
 
57616af
 
 
d1a58c9
ac6c40f
 
57616af
 
 
 
 
 
d1a58c9
57616af
 
 
d1a58c9
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
import streamlit as st

from .streamlit_utils import make_text_input

from .streamlit_utils import (
    make_multiselect,
    make_selectbox,
    make_text_area,
    make_text_input,
    make_radio,
)

N_FIELDS_ORIGINAL = 4
N_FIELDS_LANGUAGE = 12
N_FIELDS_ANNOTATIONS = 10
N_FIELDS_CONSENT = 0
N_FIELDS_PII = 0
N_FIELDS_MAINTENANCE = 0
N_FIELDS_GEM = 0

N_FIELDS = (
    N_FIELDS_ORIGINAL
    + N_FIELDS_LANGUAGE
    + N_FIELDS_ANNOTATIONS
    + N_FIELDS_CONSENT
    + N_FIELDS_PII
    + N_FIELDS_MAINTENANCE
    + N_FIELDS_GEM
)


"""
What was the selection criteria? [Describe the process for selecting instances to include in the dataset, including any tools used.]
"""


def curation_page():
    st.session_state.card_dict["curation"] = st.session_state.card_dict.get(
        "curation", {}
    )
    with st.expander("Original Curation", expanded=False):
        key_pref = ["curation", "original"]
        st.session_state.card_dict["curation"]["original"] = st.session_state.card_dict[
            "curation"
        ].get("original", {})
        make_text_area(
            label="Original curation rationale",
            key_list=key_pref + ["rationale"],
            help="Describe the curation rationale behind the original dataset(s).",
        )
        make_text_area(
            label="What was the communicative goal?",
            key_list=key_pref + ["communicative"],
            help="Describe the communicative goal that the original dataset(s) was trying to represent.",
        )
        make_radio(
            label="Is the dataset aggregated from different data sources?",
            options=["no", "yes"],
            key_list=key_pref + ["is-aggregated"],
            help="e.g. Wikipedia, movi dialogues, etc.",
        )
        make_text_area(
            label="If yes, list the sources",
            key_list=key_pref + ["aggregated-sources"],
            help="Otherwise, type N/A",
        )
    with st.expander("Language Data", expanded=False):
        key_pref = ["curation", "language"]
        st.session_state.card_dict["curation"]["language"] = st.session_state.card_dict[
            "curation"
        ].get("language", {})
        make_multiselect(
            label="How was the language data obtained?",
            options=[
                "Found",
                "Created for the dataset",
                "Crowdsourced",
                "Machine-generated",
                "Other",
            ],
            key_list=key_pref + ["obtained"],
        )
        make_multiselect(
            label="If found, where from?",
            options=["Multiple websites", "Single website", "Offline media collection", "Other", "N/A"],
            key_list=key_pref + ["found"],
            help="select N/A if none of the language data was found",
        )
        make_multiselect(
            label="If crowdsourced, where from?",
            options=[
                "Amazon Mechanical Turk",
                "Other crowdworker platform",
                "Participatory experiment",
                "Other",
                "N/A",
            ],
            key_list=key_pref + ["crowdsourced"],
            help="select N/A if none of the language data was crowdsourced",
        )
        make_text_area(
            label="If created for the dataset, describe the creation process.",
            key_list=key_pref + ["created"],
        )
        make_text_area(
            label="What further information do we have on the language producers?",
            key_list=key_pref + ["producers-description"],
            help="Provide a description of the context in which the language was produced and who produced it.",
        )
        make_text_input(
            label="If text was machine-generated for the dataset, provide a link to the generation method if available (N/A otherwise).",
            key_list=key_pref + ["machine-generated"],
            help="if the generation code is unavailable, enter N/A",
        )
        make_selectbox(
            label="Was the text validated by a different worker or a data curator?",
            options=[
                "not validated",
                "validated by crowdworker",
                "validated by data curator",
                "other",
            ],
            key_list=key_pref + ["validated"],
            help="this question is about human or human-in-the-loop validation only",
        )
        make_multiselect(
            label="In what kind of organization did the curation happen?",
            options=["industry", "academic", "independent", "other"],
            key_list=key_pref + ["organization-type"],
        )
        make_text_input(
            label="Name the organization(s).",
            key_list=key_pref + ["organization-names"],
            help="comma-separated",
        )
        make_text_area(
            label="How was the text data pre-processed? (Enter N/A if the text was not pre-processed)",
            key_list=key_pref + ["pre-processed"],
            help="List the steps in preprocessing the data for the dataset. Enter N/A if no steps were taken.",
        )
        make_selectbox(
            label="Were text instances selected or filtered?",
            options=["not filtered", "manually", "algorithmically", "hybrid"],
            key_list=key_pref + ["is-filtered"],
        )
        make_text_area(
            label="What were the selection criteria?",
            key_list=key_pref + ["filtered-criteria"],
            help="Describe the process for selecting instances to include in the dataset, including any tools used. If no selection was done, enter N/A.",
        )

    with st.expander("Structured Annotations", expanded=False):
        key_pref = ["curation", "annotations"]
        st.session_state.card_dict["curation"][
            "annotations"
        ] = st.session_state.card_dict["curation"].get("annotations", {})

        make_radio(
            label="Does the dataset have additional annotations for each instance?",
            options=["none", "found", "automatically created", "expert created", "crowd-sourced"],
            key_list=key_pref + ["origin"],
            help="Was any additional data collected?",
        )

        # TODO: If yes....
        # If expert or crowdsourced, this branch
        make_radio(
            label="What is the number of raters ",
            options=["unknown", "1", "2<n<10", "11<n<50", "51<n<100", "n>100"],
            key_list=key_pref + ["rater-number"],
            help="How many raters were used to create the additional annotations?",
        )
        make_text_area(
            label="Describe the qualifications required of an annotator.",
            key_list=key_pref + ["rater-qualifications"],
            help="e.g., languages or dialects they speak, education requirements, number of HITs (if MTurk).",
        )
        make_radio(
            label="How many annotators saw each training example?",
            options=["0", "1", "2", "3", "4", "5", ">5"],
            key_list=key_pref + ["rater-training-num"],
            help="",
        )
        make_radio(
            label="How many annotators saw each test example?",
            options=["0", "1", "2", "3", "4", "5", ">5"],
            key_list=key_pref + ["rater-test-num"],
            help="",
        )
        make_radio(
            label="Was an annotation service used?",
            options=["yes", "no", "unknown"],
            key_list=key_pref + ["rater-annotation-service-bool"],
            help="",
        )
        # TODO if yes
        make_multiselect(
            label="Which annotation services were used?",
            options=[
                "Amazon Mechanical Turk", "Prolific Academic",
                "Upwork", "Appen", "Crowdflower", "other"
            ],
            key_list=key_pref + ["rater-annotation-service"],
        )


        make_text_area(
            label="Purpose and values for each annoation",
            key_list=key_pref + ["values"],
            help="Describe the purpose and possible values for each kind of annotation.",
        )
        make_multiselect(
            label="Quality control measures?",
            options=["none", "unknown",  "validated by another rater", "validated by data curators", "validated through automated script", "other"],
            key_list=key_pref + ["quality-control"],
            help="How was annotation quality controlled for / what control measures were put in place to ensure annotation quality?",
        )
        # TODO: If not none / unknown
        make_text_area(
            label="Describe the quality control measures that were taken.",
            key_list=key_pref + ["quality-control-details"],
            help="Describe how quality was ensured in the data curation process.",
        )


    with st.expander("Consent", expanded=False):
        key_pref = ["curation", "consent"]
        st.session_state.card_dict["curation"]["consent"] = st.session_state.card_dict[
            "curation"
        ].get("consent", {})
    with st.expander("Private Identifying Information (PII)", expanded=False):
        key_pref = ["curation", "pii"]
        st.session_state.card_dict["curation"]["pii"] = st.session_state.card_dict[
            "curation"
        ].get("pii", {})
    with st.expander("Maintenance", expanded=False):
        key_pref = ["curation", "maintenance"]
        st.session_state.card_dict["curation"][
            "maintenance"
        ] = st.session_state.card_dict["curation"].get("maintenance", {})
    with st.expander("GEM Additional Curation", expanded=False):
        key_pref = ["curation", "gem"]
        st.session_state.card_dict["curation"]["gem"] = st.session_state.card_dict[
            "curation"
        ].get("gem", {})


def curation_summary():
    total_filled = sum(
        [len(dct) for dct in st.session_state.card_dict.get("curation", {}).values()]
    )
    with st.expander(
        f"Dataset Curation Completion - {total_filled} of {N_FIELDS}", expanded=False
    ):
        completion_markdown = ""
        completion_markdown += (
            f"- **Overall competion:**\n  - {total_filled} of {N_FIELDS} fields\n"
        )
        completion_markdown += f"- **Sub-section - Original Curation:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('original', {}))} of {N_FIELDS_ORIGINAL} fields\n"
        completion_markdown += f"- **Sub-section - Language Data:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('language', {}))} of {N_FIELDS_LANGUAGE} fields\n"
        completion_markdown += f"- **Sub-section - Structured Annotations:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('annotations', {}))} of {N_FIELDS_ANNOTATIONS} fields\n"
        completion_markdown += f"- **Sub-section - Consent:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('consent', {}))} of {N_FIELDS_CONSENT} fields\n"
        completion_markdown += f"- **Sub-section - PII:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('pii', {}))} of {N_FIELDS_PII} fields\n"
        completion_markdown += f"- **Sub-section - Maintenance:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('maintenance', {}))} of {N_FIELDS_MAINTENANCE} fields\n"
        completion_markdown += f"- **Sub-section - GEM Curation:**\n  - {len(st.session_state.card_dict.get('curation', {}).get('gem', {}))} of {N_FIELDS_GEM} fields\n"
        st.markdown(completion_markdown)