Spaces:
Runtime error
Runtime error
chore: Update minor formatting for the description
Browse files
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="
|
15 |
lines=1,
|
16 |
-
default="
|
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 |
βοΈ Provides an interface for user input
|
57 |
-
π Retrieves and parses the document based on the given patent information
|
58 |
π Returns summaries for the abstract, background, and/or claims.
|
59 |
|
60 |
Models explored:
|
61 |
-
|
62 |
-
https://arxiv.org/abs/2007.14062
|
63 |
-
|
64 |
-
-
|
65 |
-
|
66 |
-
https://huggingface.co/
|
67 |
-
|
68 |
-
https://arxiv.org/abs/
|
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 |
βοΈ Provides an interface for user input
|
53 |
+
π Retrieves and parses the document from Patents Google based on the given patent information
|
54 |
π Returns summaries for the abstract, background, and/or claims.
|
55 |
|
56 |
Models explored:
|
57 |
+
π€ Big Bird: Transformers for Longer Sequences
|
58 |
+
https://arxiv.org/abs/2007.14062 , https://huggingface.co/google/bigbird-pegasus-large-bigpatent
|
59 |
+
π€ T5
|
60 |
+
https://arxiv.org/pdf/1910.10683.pdf , https://huggingface.co/cnicu/t5-small-booksum
|
61 |
+
π€ 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 |
+
π€ 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 |
|