juewang commited on
Commit
bcfebc0
1 Parent(s): 9893aa5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -159
README.md CHANGED
@@ -16,7 +16,7 @@ widget:
16
  -
17
  example_title: "Sentiment Analysis"
18
  text: |-
19
- In this task, you are given Twitter posts. Your task is to label the post's emotion (as expressed by the user) as sadness, joy, love, anger, fear, or surprise.
20
 
21
  Input: I'm feeling quite sad and sorry for myself but ill snap out of it soon.
22
  Output: sadness
@@ -26,158 +26,16 @@ widget:
26
 
27
  Input: I can have for a treat or if i am feeling festive.
28
  Output:
29
- -
30
- example_title: "ADE Corpus V2"
31
- text: |-
32
- Label the sentence based on whether it is related to an adverse drug effect (ADE). Details are described below:
33
- Drugs: Names of drugs and chemicals that include brand names, trivial names, abbreviations and systematic names were annotated. Mentions of drugs or chemicals should strictly be in a therapeutic context. This category does not include the names of metabolites, reaction byproducts, or hospital chemicals (e.g. surgical equipment disinfectants).
34
- Adverse effect: Mentions of adverse effects include signs, symptoms, diseases, disorders, acquired abnormalities, deficiencies, organ damage or death that strictly occur as a consequence of drug intake.
35
- Possible labels:
36
- 1. ADE-related
37
- 2. not ADE-related
38
-
39
- Sentence: A challenge with clozapine was feasible and showed no clinical symptoms of eosinophilia.
40
- Label: not ADE-related
41
-
42
- Sentence: CONCLUSIONS: These results suggest that clozapine may cause TD; however, the prevalence is low and the severity is relatively mild, with no or mild self-reported discomfort.
43
- Label: ADE-related
44
-
45
- Sentence: Best-corrected visual acuity measurements were performed at every visit.
46
- Label: not ADE-related
47
-
48
- Sentence: These cases were considered unusual in light of the short delay of their onset after initiation of immunosuppressive therapy and their fulminant course: 3 of these patients died of PCP occurring during the first month of treatment with prednisone.
49
- Label: ADE-related
50
-
51
- Sentence: The INR should be monitored more frequently when bosentan is initiated, adjusted, or discontinued in patients taking warfarin.
52
- Label: not ADE-related
53
-
54
- Sentence: NEH must be considered in lupus patients receiving cytotoxic agents to avoid inappropriate use of corticosteroids or antibiotics in this self-limited condition.
55
- Label:
56
- -
57
- example_title: Banking77
58
- text: |-
59
- The following is a banking customer service query. Classify the query into one of the 77 categories available.
60
- Possible labels:
61
- 1. Refund_not_showing_up
62
- 2. activate_my_card
63
- 3. age_limit
64
- 4. apple_pay_or_google_pay
65
- 5. atm_support
66
- 6. automatic_top_up
67
- 7. balance_not_updated_after_bank_transfer
68
- 8. balance_not_updated_after_cheque_or_cash_deposit
69
- 9. beneficiary_not_allowed
70
- 10. cancel_transfer
71
- 11. card_about_to_expire
72
- 12. card_acceptance
73
- 13. card_arrival
74
- 14. card_delivery_estimate
75
- 15. card_linking
76
- 16. card_not_working
77
- 17. card_payment_fee_charged
78
- 18. card_payment_not_recognised
79
- 19. card_payment_wrong_exchange_rate
80
- 20. card_swallowed
81
- 21. cash_withdrawal_charge
82
- 22. cash_withdrawal_not_recognised
83
- 23. change_pin
84
- 24. compromised_card
85
- 25. contactless_not_working
86
- 26. country_support
87
- 27. declined_card_payment
88
- 28. declined_cash_withdrawal
89
- 29. declined_transfer
90
- 30. direct_debit_payment_not_recognised
91
- 31. disposable_card_limits
92
- 32. edit_personal_details
93
- 33. exchange_charge
94
- 34. exchange_rate
95
- 35. exchange_via_app
96
- 36. extra_charge_on_statement
97
- 37. failed_transfer
98
- 38. fiat_currency_support
99
- 39. get_disposable_virtual_card
100
- 40. get_physical_card
101
- 41. getting_spare_card
102
- 42. getting_virtual_card
103
- 43. lost_or_stolen_card
104
- 44. lost_or_stolen_phone
105
- 45. order_physical_card
106
- 46. passcode_forgotten
107
- 47. pending_card_payment
108
- 48. pending_cash_withdrawal
109
- 49. pending_top_up
110
- 50. pending_transfer
111
- 51. pin_blocked
112
- 52. receiving_money
113
- 53. request_refund
114
- 54. reverted_card_payment?
115
- 55. supported_cards_and_currencies
116
- 56. terminate_account
117
- 57. top_up_by_bank_transfer_charge
118
- 58. top_up_by_card_charge
119
- 59. top_up_by_cash_or_cheque
120
- 60. top_up_failed
121
- 61. top_up_limits
122
- 62. top_up_reverted
123
- 63. topping_up_by_card
124
- 64. transaction_charged_twice
125
- 65. transfer_fee_charged
126
- 66. transfer_into_account
127
- 67. transfer_not_received_by_recipient
128
- 68. transfer_timing
129
- 69. unable_to_verify_identity
130
- 70. verify_my_identity
131
- 71. verify_source_of_funds
132
- 72. verify_top_up
133
- 73. virtual_card_not_working
134
- 74. visa_or_mastercard
135
- 75. why_verify_identity
136
- 76. wrong_amount_of_cash_received
137
- 77. wrong_exchange_rate_for_cash_withdrawal
138
-
139
- Query: My card payment was not successful.
140
- Label: declined_card_payment
141
-
142
- Query: Is it possible for me to change my PIN number?
143
- Label: change_pin
144
-
145
- Query: limits on top ups
146
- Label: top_up_limits
147
-
148
- Query: I live in the EU - can I get a card?
149
- Label: country_support
150
-
151
- Query: How can I tell the source for my available funds?
152
- Label: verify_source_of_funds
153
-
154
- Query: Why am I getting declines when trying to make a purchase online?
155
- Label:
156
  -
157
- example_title: Overruling
158
  text: |-
159
- In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent, by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Label the sentence based on whether it is overruling or not.
160
- Possible labels:
161
- 1. not overruling
162
- 2. overruling
163
-
164
- Sentence: see mciver, 134 n.c.app. at 588, 518 s.e.2d at 526.
165
- Label: not overruling
166
 
167
- Sentence: to the extent that paprskar v. state, supra, applied the general test of waiver of constitutional rights set forth in johnson v. zerbst, supra, it is no longer viable.
168
- Label: overruling
169
-
170
- Sentence: narrowstep, 2010 wl 5422405, at *12.
171
- Label: not overruling
172
-
173
- Sentence: accordingly, to the extent of any conflict nemecek v. state, 621 s.w.2d 404 (tex.cr.app. 1980) is overruled.
174
- Label: overruling
175
-
176
- Sentence: the following facts are taken from the administrative record.
177
- Label: not overruling
178
-
179
- Sentence: see scott, supra at 352; commonwealth v. ruffin, 475 mass. 1003, 1004 (2016).
180
- Label:
181
  -
182
  example_title: "Tweet Eval Hate"
183
  text: |-
@@ -186,23 +44,34 @@ widget:
186
  1. hate speech
187
  2. not hate speech
188
 
189
- Tweet: #TakeAKnee trump's a chump! @user is the real deal-helping so many on his journey through greatness! Even @user can't stand #IQ45-stands to CLEAN UP while he's in prison. One hot, lucky #Immigrant babe! #OHi12 #VoteBlue @user in the #Columbus area. #BlueWave baby!
190
- Label: not hate speech
191
-
192
  Tweet: HOW REFRESHING! In South Korea, there is no such thing as 'political correctness" when it comes to dealing with Muslim refugee wannabes via @user
193
  Label: hate speech
194
 
195
  Tweet: New to Twitter-- any men on here know what the process is to get #verified?
196
  Label: not hate speech
197
 
198
- Tweet: UK Pensioner Faces 350 Lashes In Saudi Arabia why does this country exist it does nothing for migrants picks on old men no help from anyone
199
- Label: not hate speech
200
-
201
- Tweet: RT @user Her:I don't get what u want outta this relationship Him:Well, I was only looking for a bj but u kept coming back
202
- Label: not hate speech
203
-
204
  Tweet: Dont worry @user you are and will always be the most hysterical woman.
205
  Label:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
206
  ---
207
 
208
  <h1 style="font-size: 42px">GPT-JT<h1/>
 
16
  -
17
  example_title: "Sentiment Analysis"
18
  text: |-
19
+ The task is to label the post's emotion as sadness, joy, love, anger, fear, or surprise.
20
 
21
  Input: I'm feeling quite sad and sorry for myself but ill snap out of it soon.
22
  Output: sadness
 
26
 
27
  Input: I can have for a treat or if i am feeling festive.
28
  Output:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  -
30
+ example_title: "Country Currency"
31
  text: |-
32
+ Return the currency of the given country.
 
 
 
 
 
 
33
 
34
+ Input: Switzerland
35
+ Output: Swiss Franc
36
+
37
+ Input: India
38
+ Output:
 
 
 
 
 
 
 
 
 
39
  -
40
  example_title: "Tweet Eval Hate"
41
  text: |-
 
44
  1. hate speech
45
  2. not hate speech
46
 
 
 
 
47
  Tweet: HOW REFRESHING! In South Korea, there is no such thing as 'political correctness" when it comes to dealing with Muslim refugee wannabes via @user
48
  Label: hate speech
49
 
50
  Tweet: New to Twitter-- any men on here know what the process is to get #verified?
51
  Label: not hate speech
52
 
 
 
 
 
 
 
53
  Tweet: Dont worry @user you are and will always be the most hysterical woman.
54
  Label:
55
+ -
56
+ example_title: "Entity Recognition"
57
+ text: |-
58
+ Extract all the names of people, places, and organizations from the following sentences.
59
+
60
+ Sentence: Satya Nadella, the CEO of Microsoft, was visiting the Bahamas last May.
61
+ Entities: Satya Nadella, Microsoft, Bahamas
62
+
63
+ Sentence: Pacific Northwest cities include Seattle and Portland, which I have visited with Vikash.
64
+ Entities:
65
+ -
66
+ example_title: "Data Clearning"
67
+ text: |-
68
+ Format the data into a CSV file:
69
+
70
+ Input: Jane Doe jane.doe@gmail.com (520) 382 2435
71
+ Output: Jane Doe,jane.doe@gmail.com,520-382-2435
72
+
73
+ Input: Peter Lee (510) 333-2429 email: peter@yahoo.com
74
+ Output:
75
  ---
76
 
77
  <h1 style="font-size: 42px">GPT-JT<h1/>