Tom Aarsen commited on
Commit
18a08c1
1 Parent(s): 914502f

Allow for nested NER

Browse files
Files changed (1) hide show
  1. app.py +37 -16
app.py CHANGED
@@ -10,60 +10,73 @@ model = GLiNER.from_pretrained("urchade/gliner_base")
10
  examples = [
11
  [
12
  "Libretto by Marius Petipa, based on the 1822 novella ``Trilby, ou Le Lutin d'Argail`` by Charles Nodier, first presented by the Ballet of the Moscow Imperial Bolshoi Theatre on January 25/February 6 (Julian/Gregorian calendar dates), 1870, in Moscow with Polina Karpakova as Trilby and Ludiia Geiten as Miranda and restaged by Petipa for the Imperial Ballet at the Imperial Bolshoi Kamenny Theatre on January 17–29, 1871 in St. Petersburg with Adèle Grantzow as Trilby and Lev Ivanov as Count Leopold.",
13
- "person, book, location, date",
 
14
  ],
15
  [
16
  "However, both models lack other frequent DM symptoms including the fibre-type dependent atrophy, myotonia, cataract and male-infertility.",
17
- "disease, symptom"
 
18
  ],
19
  [
20
  "Synergy between signal transduction pathways is obligatory for expression of c-fos in B and T cell lines: implication for c-fos control via surface immunoglobulin and T cell antigen receptors.",
21
- "DNA, RNA, cell line, cell type, protein"
 
22
  ],
23
  [
24
  "The choice of the encoder and decoder modules of dnpg can be quite flexible, for instance long short term memory networks (lstm) or convolutional neural network (cnn).",
25
- "short acronym, long acronym"
 
26
  ],
27
  [
28
  "Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.",
29
  "person, company, location, airplane",
 
30
  ],
31
  [
32
  "Feldman is a contributor to NBC Sports Boston's ``State of the Revs`` and ``Revolution Postgame Live`` programs as well as to 98.5 the SportsHub, SiriusXM FC's MLS coverage and to other New England and national radio outlets and podcasts.",
33
  "person, company, location",
 
34
  ],
35
  [
36
  "On 25 July 1948, on the 39th anniversary of Bleriot's crossing of the English Channel, the Type 618 Nene-Viking flew Heathrow to Paris (Villacoublay) in the morning carrying letters to Bleriot's widow and son (secretary of the FAI), who met it at the airport.",
37
  "date, location, person, organization",
 
38
  ],
39
  [
40
  "Leo & Ian won the 1962 Bathurst Six Hour Classic at Mount Panorama driving a Daimler SP250 sports car, (that year the 500 mile race for touring cars were held at Phillip Island)",
41
  "person, date, location, organization, competition",
 
42
  ],
43
  [
44
  "The Shore Line route of the CNS & M until 1955 served, from south to north, the Illinois communities of Chicago, Evanston, Wilmette, Kenilworth, Winnetka, Glencoe, Highland Park, Highwood, Fort Sheridan, Lake Forest, Lake Bluff, North Chicago, Waukegan, Zion, and Winthrop Harbor as well as Kenosha, Racine, and Milwaukee (the ``KRM'') in Wisconsin.",
45
  "location, organization, date",
 
46
  ],
47
  [
48
  "Comet C/2006 M4 (SWAN) is a non-periodic comet discovered in late June 2006 by Robert D. Matson of Irvine, California and Michael Mattiazzo of Adelaide, South Australia in publicly available images of the Solar and Heliospheric Observatory (SOHO).",
49
  "person, organization, date, location",
 
50
  ],
51
  [
52
  "From November 29, 2011 to March 31, 2012, Karimloo returned to ``Les Misérables`` to play the lead role of Jean Valjean at The Queen's Theatre, London, for which he won the 2013 Theatregoers' Choice Award for Best Takeover in a Role.",
53
  "person, actor, award, date, location",
 
54
  ],
55
  [
56
  "A Mexicali health clinic supported by former Baja California gubernatorial candidate Enrique Acosta Fregoso (PRI) was closed on June 15 after selling a supposed COVID-19 ``cure'' for between MXN $10,000 and $50,000.",
57
  "location, organization, person, date, currency",
 
58
  ],
59
  [
60
  "Built in 1793, it was the home of Mary Young Pickersgill when she moved to Baltimore in 1806 and the location where she later sewed the ``Star Spangled Banner'', in 1813, the huge out-sized garrison flag that flew over Fort McHenry at Whetstone Point in Baltimore Harbor in the summer of 1814 during the British Royal Navy attack in the Battle of Baltimore during the War of 1812.",
61
  "date, person, location, organization, event, flag",
62
- ]
 
63
  ]
64
 
65
 
66
- def ner(text, labels: str) -> Dict[str, Union[str, int, float]]:
67
  labels = labels.split(",")
68
  return {
69
  "text": text,
@@ -75,7 +88,7 @@ def ner(text, labels: str) -> Dict[str, Union[str, int, float]]:
75
  "end": entity["end"],
76
  "score": 0,
77
  }
78
- for entity in model.predict_entities(text, labels)
79
  ],
80
  }
81
 
@@ -147,24 +160,32 @@ with gr.Blocks(title="GLiNER-base") as demo:
147
  input_text = gr.Textbox(
148
  value=examples[0][0], label="Text input", placeholder="Enter your text here"
149
  )
150
- labels = gr.Textbox(
151
- value=examples[0][1],
152
- label="Labels",
153
- placeholder="Enter your labels here (comma separated)",
154
- )
 
 
 
 
 
 
 
 
155
  output = gr.HighlightedText(label="Predicted Entities")
156
  submit_btn = gr.Button("Submit")
157
  examples = gr.Examples(
158
  examples,
159
  fn=ner,
160
- inputs=[input_text, labels],
161
  outputs=output,
162
  cache_examples=True,
163
  )
164
 
165
  # Submitting
166
- input_text.submit(fn=ner, inputs=[input_text, labels], outputs=output)
167
- submit_btn.click(fn=ner, inputs=[input_text, labels], outputs=output)
168
 
169
  demo.queue()
170
- demo.launch()
 
10
  examples = [
11
  [
12
  "Libretto by Marius Petipa, based on the 1822 novella ``Trilby, ou Le Lutin d'Argail`` by Charles Nodier, first presented by the Ballet of the Moscow Imperial Bolshoi Theatre on January 25/February 6 (Julian/Gregorian calendar dates), 1870, in Moscow with Polina Karpakova as Trilby and Ludiia Geiten as Miranda and restaged by Petipa for the Imperial Ballet at the Imperial Bolshoi Kamenny Theatre on January 17–29, 1871 in St. Petersburg with Adèle Grantzow as Trilby and Lev Ivanov as Count Leopold.",
13
+ "person, book, location, date, actor, character",
14
+ True,
15
  ],
16
  [
17
  "However, both models lack other frequent DM symptoms including the fibre-type dependent atrophy, myotonia, cataract and male-infertility.",
18
+ "disease, symptom",
19
+ False,
20
  ],
21
  [
22
  "Synergy between signal transduction pathways is obligatory for expression of c-fos in B and T cell lines: implication for c-fos control via surface immunoglobulin and T cell antigen receptors.",
23
+ "DNA, RNA, cell line, cell type, protein",
24
+ False,
25
  ],
26
  [
27
  "The choice of the encoder and decoder modules of dnpg can be quite flexible, for instance long short term memory networks (lstm) or convolutional neural network (cnn).",
28
+ "short acronym, long acronym",
29
+ False,
30
  ],
31
  [
32
  "Amelia Earhart flew her single engine Lockheed Vega 5B across the Atlantic to Paris.",
33
  "person, company, location, airplane",
34
+ True,
35
  ],
36
  [
37
  "Feldman is a contributor to NBC Sports Boston's ``State of the Revs`` and ``Revolution Postgame Live`` programs as well as to 98.5 the SportsHub, SiriusXM FC's MLS coverage and to other New England and national radio outlets and podcasts.",
38
  "person, company, location",
39
+ False,
40
  ],
41
  [
42
  "On 25 July 1948, on the 39th anniversary of Bleriot's crossing of the English Channel, the Type 618 Nene-Viking flew Heathrow to Paris (Villacoublay) in the morning carrying letters to Bleriot's widow and son (secretary of the FAI), who met it at the airport.",
43
  "date, location, person, organization",
44
+ False,
45
  ],
46
  [
47
  "Leo & Ian won the 1962 Bathurst Six Hour Classic at Mount Panorama driving a Daimler SP250 sports car, (that year the 500 mile race for touring cars were held at Phillip Island)",
48
  "person, date, location, organization, competition",
49
+ False,
50
  ],
51
  [
52
  "The Shore Line route of the CNS & M until 1955 served, from south to north, the Illinois communities of Chicago, Evanston, Wilmette, Kenilworth, Winnetka, Glencoe, Highland Park, Highwood, Fort Sheridan, Lake Forest, Lake Bluff, North Chicago, Waukegan, Zion, and Winthrop Harbor as well as Kenosha, Racine, and Milwaukee (the ``KRM'') in Wisconsin.",
53
  "location, organization, date",
54
+ False,
55
  ],
56
  [
57
  "Comet C/2006 M4 (SWAN) is a non-periodic comet discovered in late June 2006 by Robert D. Matson of Irvine, California and Michael Mattiazzo of Adelaide, South Australia in publicly available images of the Solar and Heliospheric Observatory (SOHO).",
58
  "person, organization, date, location",
59
+ False,
60
  ],
61
  [
62
  "From November 29, 2011 to March 31, 2012, Karimloo returned to ``Les Misérables`` to play the lead role of Jean Valjean at The Queen's Theatre, London, for which he won the 2013 Theatregoers' Choice Award for Best Takeover in a Role.",
63
  "person, actor, award, date, location",
64
+ False,
65
  ],
66
  [
67
  "A Mexicali health clinic supported by former Baja California gubernatorial candidate Enrique Acosta Fregoso (PRI) was closed on June 15 after selling a supposed COVID-19 ``cure'' for between MXN $10,000 and $50,000.",
68
  "location, organization, person, date, currency",
69
+ False,
70
  ],
71
  [
72
  "Built in 1793, it was the home of Mary Young Pickersgill when she moved to Baltimore in 1806 and the location where she later sewed the ``Star Spangled Banner'', in 1813, the huge out-sized garrison flag that flew over Fort McHenry at Whetstone Point in Baltimore Harbor in the summer of 1814 during the British Royal Navy attack in the Battle of Baltimore during the War of 1812.",
73
  "date, person, location, organization, event, flag",
74
+ False,
75
+ ],
76
  ]
77
 
78
 
79
+ def ner(text, labels: str, nested_ner: bool) -> Dict[str, Union[str, int, float]]:
80
  labels = labels.split(",")
81
  return {
82
  "text": text,
 
88
  "end": entity["end"],
89
  "score": 0,
90
  }
91
+ for entity in model.predict_entities(text, labels, flat_ner=not nested_ner)
92
  ],
93
  }
94
 
 
160
  input_text = gr.Textbox(
161
  value=examples[0][0], label="Text input", placeholder="Enter your text here"
162
  )
163
+ with gr.Row() as row:
164
+ labels = gr.Textbox(
165
+ value=examples[0][1],
166
+ label="Labels",
167
+ placeholder="Enter your labels here (comma separated)",
168
+ scale=1,
169
+ )
170
+ nested_ner = gr.Checkbox(
171
+ value=examples[0][2],
172
+ label="Nested NER",
173
+ info="Allow for nested NER?",
174
+ scale=0,
175
+ )
176
  output = gr.HighlightedText(label="Predicted Entities")
177
  submit_btn = gr.Button("Submit")
178
  examples = gr.Examples(
179
  examples,
180
  fn=ner,
181
+ inputs=[input_text, labels, nested_ner],
182
  outputs=output,
183
  cache_examples=True,
184
  )
185
 
186
  # Submitting
187
+ input_text.submit(fn=ner, inputs=[input_text, labels, nested_ner], outputs=output)
188
+ submit_btn.click(fn=ner, inputs=[input_text, labels, nested_ner], outputs=output)
189
 
190
  demo.queue()
191
+ demo.launch(debug=True)