Spaces:
Runtime error
Runtime error
File size: 3,632 Bytes
dee848c 8ecadd9 8bcebcf 85e8ccf 926f2cd 8ecadd9 b796027 8ecadd9 6783b8c 8ecadd9 b796027 ea5dcc8 8ecadd9 ea5dcc8 8ecadd9 6783b8c 8ecadd9 a18ded0 8ecadd9 24df5eb 8ecadd9 b796027 8ecadd9 b796027 6783b8c b796027 4d179ce 6783b8c b0a71d3 9b174bd 6783b8c 9b174bd 6783b8c 53719a8 8ecadd9 ea5dcc8 4d179ce 85e8ccf b796027 dee848c 85e8ccf |
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 |
import gradio as gr
from util import summarizer, textproc
from util.examples import entries
import importlib
importlib.reload(summarizer)
importlib.reload(textproc)
model_collection = summarizer.init_models()
patent_summarizer = summarizer.PatentSummarizer(model_collection)
iface = gr.Interface(
patent_summarizer.pipeline,
theme="huggingface",
examples=entries,
examples_per_page=4,
inputs=[
gr.inputs.Textbox(label="Patent Information",
placeholder="US10125002B2 or https://patents.google.com/patent/US10125002B2 ...",
lines=1,
default="US10125002B2"),
gr.inputs.CheckboxGroup(summarizer.summary_options,
default=summarizer.summary_options,
label="Summaries to Generate"),
gr.inputs.Dropdown(summarizer.model_names,
default=summarizer.model_names[3],
label="Abstract Model"),
gr.inputs.Dropdown(summarizer.model_names,
default=summarizer.model_names[0],
label="Background Model"),
gr.inputs.Dropdown(summarizer.model_names,
default=summarizer.model_names[2],
label="Claims Model"),
gr.inputs.Checkbox(default=True,
label="Collate Claims",
optional=False),
gr.inputs.Slider(minimum=250,
maximum=1000,
step=10,
default=250,
label="Input Document Word Limit"),
],
outputs=[
gr.outputs.Textbox(label="Abstract Summary"),
gr.outputs.Textbox(label="Background Summary"),
gr.outputs.Textbox(label="Sample Claims Summary")
],
title="Patent Summarizer 📖",
description="""
✏️ Provides an interface for user input
📂 Retrieves and parses the document from Patents Google
📑 Returns summaries for the abstract, background, and/or claims.
Check the end of the app for more details.
""",
article="""
v.1.0.0
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.
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.
Notes:
- Increasing 'Input Document Word Limit' may improve results but will
cause inference time to increase
- Setting 'Collate Claims' to False will apply summarization across
individual claims. Doing so will greatly increase inference time.
Models explored:
🤖 Big Bird: Transformers for Longer Sequences
https://arxiv.org/abs/2007.14062 , https://huggingface.co/google/bigbird-pegasus-large-bigpatent
🤖 T5
https://arxiv.org/pdf/1910.10683.pdf , https://huggingface.co/cnicu/t5-small-booksum
🤖 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
https://arxiv.org/abs/1910.13461, https://huggingface.co/sshleifer/distilbart-cnn-6-6
🤖 PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
https://arxiv.org/abs/1912.08777 , https://huggingface.co/google/pegasus-xsum
"""
)
iface.launch(enable_queue=True) |