First version

.gitignore

@@ -0,0 +1,167 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# End of https://www.toptal.com/developers/gitignore/api/python

app.py

@@ -0,0 +1,54 @@
+import streamlit as st
+import pandas as pd
+from extraction.keyphrase_extraction_pipeline import KeyphraseExtractionPipeline
+from extraction.keyphrase_generation_pipeline import KeyphraseGenerationPipeline
+import orjson
+
+
+if "config" not in st.session_state:
+    with open("config.json", "r") as f:
+        content = f.read()
+    st.session_state.config = orjson.loads(content)
+
+st.set_page_config(
+    page_icon="🔑",
+    page_title="Keyphrase extraction/generation with Transformers",
+    layout="wide",
+    initial_sidebar_state="auto",
+)
+
+
+@st.cache(allow_output_mutation=True)
+def load_pipeline(chosen_model):
+    if "keyphrase-extraction" in chosen_model:
+        return KeyphraseExtractionPipeline(chosen_model)
+    elif "keyphrase-generation" in chosen_model:
+        return KeyphraseGenerationPipeline(chosen_model)
+
+
+def extract_keyphrases():
+    st.session_state.keyphrases = pipe(st.session_state.input_text)
+
+
+st.header("🔑 Keyphrase extraction/generation with Transformers")
+col1, col2 = st.columns([1, 3])
+
+col1.subheader("Select model")
+chosen_model = col1.selectbox(
+    "Choose your model:",
+    st.session_state.config.get("models"),
+)
+st.session_state.chosen_model = chosen_model
+
+pipe = load_pipeline(st.session_state.chosen_model)
+
+col2.subheader("Input your text")
+st.session_state.input_text = col2.text_area(
+    "Input", st.session_state.config.get("example_text"), height=150
+)
+pressed = col2.button("Extract", on_click=extract_keyphrases)
+
+if pressed:
+    col2.subheader("🐧 Output")
+    df = pd.DataFrame(data=st.session_state.keyphrases, columns=["Keyphrases"])
+    col2.table(df)

config.json

@@ -0,0 +1,13 @@
+{
+  "example_text": "Keyphrase extraction is a technique in text analysis where you extract the important keyphrases from a text. Since this is a time-consuming process, Artificial Intelligence is used to automate it. Currently, classical machine learning methods, that use statistics and linguistics, are widely used for the extraction process. The fact that these methods have been widely used in the community has the advantage that there are many easy-to-use libraries. Now with the recent innovations in deep learning methods (such as recurrent neural networks and transformers, GANS, ... ), keyphrase extraction can be improved. These new methods also focus on the semantics and context of a document, which is quite an improvement.",
+  "models": [
+    "DeDeckerThomas/keyphrase-extraction-kbir-inspec",
+    "DeDeckerThomas/keyphrase-extraction-distilbert-inspec",
+    "DeDeckerThomas/keyphrase-extraction-distilbert-openkp",
+    "DeDeckerThomas/keyphrase-extraction-distilbert-kptimes",
+    "DeDeckerThomas/keyphrase-extraction-kbir-kpcrowd",
+    "DeDeckerThomas/keyphrase-generation-keybart-inspec",
+    "DeDeckerThomas/keyphrase-generation-t5-small-inspec",
+    "DeDeckerThomas/keyphrase-generation-t5-small-openkp"
+  ]
+}

extraction/keyphrase_extraction_pipeline.py

@@ -0,0 +1,24 @@
+from transformers import (
+    TokenClassificationPipeline,
+    AutoModelForTokenClassification,
+    AutoTokenizer,
+)
+from transformers.pipelines import AggregationStrategy
+import numpy as np
+
+
+class KeyphraseExtractionPipeline(TokenClassificationPipeline):
+    def __init__(self, model, *args, **kwargs):
+        super().__init__(
+            model=AutoModelForTokenClassification.from_pretrained(model),
+            tokenizer=AutoTokenizer.from_pretrained(model),
+            *args,
+            **kwargs
+        )
+
+    def postprocess(self, model_outputs):
+        results = super().postprocess(
+            model_outputs=model_outputs,
+            aggregation_strategy=AggregationStrategy.SIMPLE,
+        )
+        return np.unique([result.get("word").strip() for result in results])

extraction/keyphrase_generation_pipeline.py

@@ -0,0 +1,28 @@
+from transformers import (
+    Text2TextGenerationPipeline,
+    AutoModelForSeq2SeqLM,
+    AutoTokenizer,
+)
+
+
+class KeyphraseGenerationPipeline(Text2TextGenerationPipeline):
+    def __init__(self, model, keyphrase_sep_token=";", *args, **kwargs):
+        super().__init__(
+            model=AutoModelForSeq2SeqLM.from_pretrained(model),
+            tokenizer=AutoTokenizer.from_pretrained(model),
+            *args,
+            **kwargs
+        )
+        self.keyphrase_sep_token = keyphrase_sep_token
+
+    def postprocess(self, model_outputs):
+        results = super().postprocess(model_outputs=model_outputs)
+        return [
+            [
+                keyphrase.strip()
+                for keyphrase in result.get("generated_text").split(
+                    self.keyphrase_sep_token
+                )
+            ]
+            for result in results
+        ][0]