amielle commited on
Commit
ea5dcc8
β€’
1 Parent(s): 24df5eb

chore: Update minor formatting for the description

Browse files
Files changed (1) hide show
  1. app.py +13 -21
app.py CHANGED
@@ -11,9 +11,9 @@ iface = gr.Interface(
11
  examples_per_page=4,
12
  inputs=[
13
  gr.inputs.Textbox(label="Patent Information",
14
- placeholder="US9820315B2 or https://patents.google.com/patent/US9820315B2 ...",
15
  lines=1,
16
- default="US9820315B2"),
17
  gr.inputs.CheckboxGroup(summarizer.summary_options,
18
  default=summarizer.summary_options,
19
  label="Summaries to Generate"),
@@ -44,32 +44,24 @@ iface = gr.Interface(
44
  description="""
45
  v.1.0.0
46
 
47
- Reading through patent documents is oftentimes a long and tedious task.
48
- There are cases wherein one has to manually go through several pages
49
- in order to determine if the patent is relevant to the prior art search.
50
 
51
- This application is meant to automate the initial phase of going through
52
- patents so that the potential inventor or researcher may lessen the time
53
- spent trying to filter documents.
54
 
55
  The Patent Summarizer:
56
  ✏️ Provides an interface for user input
57
- πŸ“‚ Retrieves and parses the document based on the given patent information
58
  πŸ“‘ Returns summaries for the abstract, background, and/or claims.
59
 
60
  Models explored:
61
- - Big Bird: Transformers for Longer Sequences
62
- https://arxiv.org/abs/2007.14062
63
- https://huggingface.co/google/bigbird-pegasus-large-bigpatent
64
- - T5
65
- https://arxiv.org/pdf/1910.10683.pdf
66
- https://huggingface.co/cnicu/t5-small-booksum
67
- - BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
68
- https://arxiv.org/abs/1910.13461
69
- https://huggingface.co/sshleifer/distilbart-cnn-6-6
70
- - PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
71
- https://arxiv.org/abs/1912.08777
72
- https://huggingface.co/google/pegasus-xsum
73
  """
74
  )
75
 
 
11
  examples_per_page=4,
12
  inputs=[
13
  gr.inputs.Textbox(label="Patent Information",
14
+ placeholder="US10125002B2 or https://patents.google.com/patent/US10125002B2 ...",
15
  lines=1,
16
+ default="US10125002B2"),
17
  gr.inputs.CheckboxGroup(summarizer.summary_options,
18
  default=summarizer.summary_options,
19
  label="Summaries to Generate"),
 
44
  description="""
45
  v.1.0.0
46
 
47
+ Reading through patent documents is oftentimes a long and tedious task. There are cases wherein one has to manually go through several pages in order to determine if the patent is relevant to the prior art search.
 
 
48
 
49
+ This application is meant to automate the initial phase of going through patents so that the potential inventor or researcher may lessen the time spent trying to filter documents.
 
 
50
 
51
  The Patent Summarizer:
52
  ✏️ Provides an interface for user input
53
+ πŸ“‚ Retrieves and parses the document from Patents Google based on the given patent information
54
  πŸ“‘ Returns summaries for the abstract, background, and/or claims.
55
 
56
  Models explored:
57
+ πŸ€– Big Bird: Transformers for Longer Sequences
58
+ https://arxiv.org/abs/2007.14062 , https://huggingface.co/google/bigbird-pegasus-large-bigpatent
59
+ πŸ€– T5
60
+ https://arxiv.org/pdf/1910.10683.pdf , https://huggingface.co/cnicu/t5-small-booksum
61
+ πŸ€– BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
62
+ https://arxiv.org/abs/1910.13461, https://huggingface.co/sshleifer/distilbart-cnn-6-6
63
+ πŸ€– PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
64
+ https://arxiv.org/abs/1912.08777 , https://huggingface.co/google/pegasus-xsum
 
 
 
 
65
  """
66
  )
67