diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
index 3180c29..d9744af 100644
--- a/.github/workflows/deploy.yml
+++ b/.github/workflows/deploy.yml
@@ -25,7 +25,8 @@ jobs:
 
       - name: Publish
         run: |
-          poetry publish -u ${{ secrets.PYPI_UNAME }} -p ${{ secrets.PYPI_PWD }}
+          poetry config pypi-token.pypi ${{ secrets.PYPI_TOKEN }}
+          poetry publish
       - name: Upload binaries to release
         uses: softprops/action-gh-release@v1
         if: ${{startsWith(github.ref, 'refs/tags/') }}
diff --git a/README.rst b/README.rst
index f30a808..3c9cc75 100644
--- a/README.rst
+++ b/README.rst
@@ -1,7 +1,7 @@
 =====
 SINr
 =====
-|languages| |downloads| |license| |version| |cpython| |wheel| |python| |docs| |activity| |contributors| |quality| |build|
+|languages| |downloads| |license| |version| |cpython| |wheel| |python| |activity| |contributors|
 
 *SINr* is an open-source tool to efficiently compute graph and word
 embeddings. Its aim is to provide sparse interpretable vectors from a
@@ -50,7 +50,8 @@ Usage example
 =============
 
 To get started using *SINr* to build graph and word embeddings, have a
-look at the `notebook <./notebooks>`__ directory.
+look at the `notebook <https://github.com/SINr-Embeddings/sinr/tree/main/notebooks>`_ 
+directory.
 
 Here is a minimum working example of *SINr*
 
@@ -132,7 +133,7 @@ to disccus the changes to be made.
 License
 =======
 
-Released under `CeCILL 2.1 <https://cecill.info/>`__, see `LICENSE <./LICENSE>`__ for more details.
+Released under `CeCILL 2.1 <https://cecill.info/>`__, see `LICENSE <https://github.com/SINr-Embeddings/sinr/blob/main/LICENSE>`__ for more details.
 
 Publications
 ============
@@ -141,7 +142,7 @@ Publications
 find *SINr* useful for your own research, please cite the appropriate
 papers from the list below. Publications can also be found on
 `publications page in the
-documentation <https://sinr-embeddings.github.io/sinr/_build/html/publications.html>`__.
+documentation <https://sinr-embeddings.github.io/sinr/publications.html>`__.
 
 **Initial SINr paper, 2021**
 
@@ -184,8 +185,6 @@ documentation <https://sinr-embeddings.github.io/sinr/_build/html/publications.h
 .. |cpython| image:: https://img.shields.io/pypi/implementation/sinr
 .. |wheel| image:: https://img.shields.io/pypi/wheel/sinr
 .. |python| image:: https://img.shields.io/pypi/pyversions/sinr
-.. |docs| image:: https://img.shields.io/website?url=https%3A%2F%2Fsinr-embeddings.github.io%2Fsinr%2F_build%2Fhtml%2Findex.html
 .. |activity| image:: https://img.shields.io/github/commit-activity/y/SINr-Embeddings/sinr
 .. |contributors| image:: https://img.shields.io/github/contributors/SINr-Embeddings/sinr
-.. |quality| image:: https://scrutinizer-ci.com/g/SINr-Embeddings/sinr/badges/quality-score.png?b=main
-.. |build| image:: https://scrutinizer-ci.com/g/SINr-Embeddings/sinr/badges/build.png?b=main
+
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 4a4187b..5071122 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -7,8 +7,8 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
 project = 'SINr'
-copyright = '2023, Thibault Prouteau, Nicolas Dugué, Simon Guillot'
-author = 'Thibault Prouteau, Nicolas Dugué, Simon Guillot'
+copyright = '2024, Thibault Prouteau, Nicolas Dugué, Simon Guillot, Anna Béranger'
+author = 'Thibault Prouteau, Nicolas Dugué, Simon Guillot, Anna Béranger'
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
diff --git a/docs/source/presentation.rst b/docs/source/presentation.rst
index f3c0edf..b1d3878 100644
--- a/docs/source/presentation.rst
+++ b/docs/source/presentation.rst
@@ -4,7 +4,7 @@
 Overview
 ============
 
-|languages| |downloads| |license| |version| |cpython| |wheel| |python| |docs| |activity| |contributors| |quality| |build|
+|languages| |downloads| |license| |version| |cpython| |wheel| |python| |activity| |contributors|
 
 *SINr* is an open-source tool to efficiently compute graph and word
 embeddings. Its aim is to provide sparse interpretable vectors from a
@@ -38,24 +38,12 @@ Requirements
 Install
 -------
 
-**SINr** can be installed through ``pip`` or from source using ``poetry`` directives.
+**SINr** can be installed through ``pip``.
 
-..  tabs::
+.. code:: bash
 
-    ..  code-tab:: zsh pip
-
-        #Activate conda environment
-        conda activate sinr
-        pip install sinr
-
-    ..  code-tab:: zsh from source
-
-        #Activate conda environment
-        conda activate sinr
-        git clone git@github.com:SINr-Embeddings/sinr.git
-        cd sinr
-        pip install poetry #poetry solves dependencies and installs SINr
-        poetry install #Installs SINr based on the pyproject.toml file
+   conda activate sinr # activate conda environment
+   pip install sinr
 
 
 Usage example
@@ -69,30 +57,66 @@ Here is a minimum working example of SINr :
 
 .. code:: python
 
-    import urllib
-    import io
-    import gzip
-    import networkit as nk
-    import sinr.graph_embeddings as ge
-
-
-    url = "https://snap.stanford.edu/data/wiki-Vote.txt.gz"
-    graph_file = "wikipedia-votes.txt"
-    # Read a graph from SNAP
-    sock = urllib.request.urlopen(url)  # open URL
-    s = io.BytesIO(sock.read())  # read into BytesIO "file"
-    sock.close()
-    with gzip.open(s, "rt") as f_in:
-        with open(graph_file, "wt") as f_out:
-            f_out.writelines(f_in.readlines())
-    # Initialize a networkit.Graph object from SNAP graph
-    G = nk.readGraph(graph_file, nk.Format.SNAP)
-
-    # Build a SINr model and extract embeddings
-    model = ge.SINr.load_from_graph(G)
-    model.run(algo=nk.community.PLM(G))
-    embeddings = model.get_nr()
-    print(embeddings)
+       import nltk # For textual resources
+
+       import sinr.text.preprocess as ppcs
+       from sinr.text.cooccurrence import Cooccurrence
+       from sinr.text.pmi import pmi_filter
+       import sinr.graph_embeddings as ge
+       import sinr.text.evaluate as ev
+
+       # Get a textual corpus
+       # For example, texts from the Project Gutenberg electronic text archive,
+       # hosted at http://www.gutenberg.org/
+       nltk.download('gutenberg')
+       gutenberg = nltk.corpus.gutenberg # contains 25,000 free electronic books
+       file = open("my_corpus.txt", "w")
+       file.write(gutenberg.raw())
+       file.close()
+
+       # Preprocess corpus
+       vrt_maker = ppcs.VRTMaker(ppcs.Corpus(ppcs.Corpus.REGISTER_WEB,
+                                             ppcs.Corpus.LANGUAGE_EN,
+                                             "my_corpus.txt"),
+                                             ".", n_jobs=8)
+       vrt_maker.do_txt_to_vrt()
+       sentences = ppcs.extract_text("my_corpus.vrt", min_freq=20)
+
+       # Construct cooccurrence matrix
+       c = Cooccurrence()
+       c.fit(sentences, window=5)
+       c.matrix = pmi_filter(c.matrix)
+       c.save("my_cooc_matrix.pk")
+
+       # Train SINr model
+       model = ge.SINr.load_from_cooc_pkl("my_cooc_matrix.pk")
+       commu = model.detect_communities(gamma=10)
+       model.extract_embeddings(commu)
+
+       # Construct SINrVectors to manipulate the model
+       sinr_vec = ge.InterpretableWordsModelBuilder(model,
+                                                    'my_sinr_vectors',
+                                                    n_jobs=8,
+                                                    n_neighbors=25).build()
+       sinr_vec.save()
+
+       # Sparsify vectors for better interpretability and performances
+       sinr_vec.sparsify(100)
+
+       # Evaluate the model with the similarity task
+       print('\nResults of the similarity evaluation :')
+       print(ev.similarity_MEN_WS353_SCWS(sinr_vec))
+
+       # Explore word vectors and dimensions of the model
+       print("\nDimensions activated by the word 'apple' :")
+       print(sinr_vec.get_obj_stereotypes('apple', topk_dim=5, topk_val=3))
+
+       print("\nWords similar to 'apple' :")
+       print(sinr_vec.most_similar('apple'))
+
+       # Load an existing SinrVectors object
+       sinr_vec = ge.SINrVectors('my_sinr_vectors')
+       sinr_vec.load()
 
 
 Contributing
@@ -115,13 +139,35 @@ Publications can also be found on :ref:`Publications`.
 
 **Initial SINr paper, 2021**
 
+-  Thibault Prouteau, Victor Connes, Nicolas Dugué, Anthony Perez,
+   Jean-Charles Lamirel, et al.. SINr: Fast Computing of Sparse
+   Interpretable Node Representations is not a Sin!. Advances in
+   Intelligent Data Analysis XIX, 19th International Symposium on
+   Intelligent Data Analysis, IDA 2021, Apr 2021, Porto, Portugal.
+   pp.325-337,
+   ⟨\ `10.1007/978-3-030-74251-5_26 <https://dx.doi.org/10.1007/978-3-030-74251-5_26>`__\ ⟩.
+   `⟨hal-03197434⟩ <https://hal.science/hal-03197434>`__
+
+**Interpretability of SINr embedding**
+
+-  Thibault Prouteau, Nicolas Dugué, Nathalie Camelin, Sylvain Meignier.
+   Are Embedding Spaces Interpretable? Results of an Intrusion Detection
+   Evaluation on a Large French Corpus. LREC 2022, Jun 2022, Marseille,
+   France. `⟨hal-03770444⟩ <https://hal.science/hal-03770444>`__
 
+**Sparsity of SINr embedding**
 
-- Thibault Prouteau, Victor Connes, Nicolas Dugué, Anthony Perez, Jean-Charles Lamirel, et al.. SINr: Fast Computing of Sparse Interpretable Node Representations is not a Sin!. Advances in Intelligent Data Analysis XIX, 19th International Symposium on Intelligent Data Analysis, IDA 2021, Apr 2021, Porto, Portugal. pp.325-337, ⟨`10.1007/978-3-030-74251-5_26 <https://dx.doi.org/10.1007/978-3-030-74251-5_26>`_⟩. `⟨hal-03197434⟩ <https://hal.science/hal-03197434>`_
+-  Simon Guillot, Thibault Prouteau, Nicolas Dugué.
+   Sparser is better: one step closer to word embedding interpretability.
+   IWCS 2023, Nancy, France.
+   `⟨hal-04321407⟩ <https://hal.science/hal-04321407>`__
 
-**Interpretability of SINr embeddings, 2022**
+**Filtering dimensions of SINr embedding**
 
-- Thibault Prouteau, Nicolas Dugué, Nathalie Camelin, Sylvain Meignier. Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus. LREC 2022, Jun 2022, Marseille, France. `⟨hal-03770444⟩ <https://hal.science/hal-03770444>`_
+-  Anna Béranger, Nicolas Dugué, Simon Guillot, Thibault Prouteau.
+   Filtering communities in word co-occurrence networks to foster the
+   emergence of meaning. Complex Networks 2023, Menton, France.
+   `⟨hal-04398742⟩ <https://hal.science/hal-04398742>`__
 
 .. |languages| image:: https://img.shields.io/github/languages/count/SINr-Embeddings/sinr
 .. |downloads| image:: https://img.shields.io/pypi/dm/sinr
@@ -130,8 +176,5 @@ Publications can also be found on :ref:`Publications`.
 .. |cpython| image:: https://img.shields.io/pypi/implementation/sinr
 .. |wheel| image:: https://img.shields.io/pypi/wheel/sinr
 .. |python| image:: https://img.shields.io/pypi/pyversions/sinr
-.. |docs| image:: https://img.shields.io/website?url=https%3A%2F%2Fsinr-embeddings.github.io%2Fsinr%2F_build%2Fhtml%2Findex.html
 .. |activity| image:: https://img.shields.io/github/commit-activity/y/SINr-Embeddings/sinr
 .. |contributors| image:: https://img.shields.io/github/contributors/SINr-Embeddings/sinr
-.. |quality| image:: https://scrutinizer-ci.com/g/SINr-Embeddings/sinr/badges/quality-score.png?b=main
-.. |build| image:: https://scrutinizer-ci.com/g/SINr-Embeddings/sinr/badges/build.png?b=main
diff --git a/docs/source/publications.rst b/docs/source/publications.rst
index f16fc72..9d21b3c 100644
--- a/docs/source/publications.rst
+++ b/docs/source/publications.rst
@@ -6,10 +6,20 @@ Publications
 **Initial SINr paper, 2021**
 
 
-- Thibault Prouteau, Victor Connes, Nicolas Dugué, Anthony Perez, Jean-Charles Lamirel, et al.. SINr: Fast Computing of Sparse Interpretable Node Representations is not a Sin!. Advances in Intelligent Data Analysis XIX, 19th International Symposium on Intelligent Data Analysis, IDA 2021, Apr 2021, Porto, Portugal. pp.325-337, ⟨`10.1007/978-3-030-74251-5_26 <https://dx.doi.org/10.1007/978-3-030-74251-5_26>`_⟩. `⟨hal-03197434⟩ <https://hal.science/hal-03197434>`_
+-  Thibault Prouteau, Victor Connes, Nicolas Dugué, Anthony Perez, Jean-Charles Lamirel, et al.. SINr: Fast Computing of Sparse Interpretable Node Representations is not a Sin!. Advances in Intelligent Data Analysis XIX, 19th International Symposium on Intelligent Data Analysis, IDA 2021, Apr 2021, Porto, Portugal. pp.325-337, ⟨\ `10.1007/978-3-030-74251-5_26 <https://dx.doi.org/10.1007/978-3-030-74251-5_26>`__\ ⟩.
+   `⟨hal-03197434⟩ <https://hal.science/hal-03197434>`__
 
+**Interpretability of SINr embedding**
 
-**Interpretability of SINr embeddings, 2022**
 
+-  Thibault Prouteau, Nicolas Dugué, Nathalie Camelin, Sylvain Meignier. Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus. LREC 2022, Jun 2022, Marseille, France. `⟨hal-03770444⟩ <https://hal.science/hal-03770444>`__
 
-- Thibault Prouteau, Nicolas Dugué, Nathalie Camelin, Sylvain Meignier. Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus. LREC 2022, Jun 2022, Marseille, France. `⟨hal-03770444⟩ <https://hal.science/hal-03770444>`_
\ No newline at end of file
+**Sparsity of SINr embedding**
+
+
+-  Simon Guillot, Thibault Prouteau, Nicolas Dugué. Sparser is better: one step closer to word embedding interpretability. IWCS 2023, Nancy, France. `⟨hal-04321407⟩ <https://hal.science/hal-04321407>`__
+
+**Filtering dimensions of SINr embedding**
+
+
+-  Anna Béranger, Nicolas Dugué, Simon Guillot, Thibault Prouteau. Filtering communities in word co-occurrence networks to foster the emergence of meaning. Complex Networks 2023, Menton, France. `⟨hal-04398742v1⟩ <https://hal.science/hal-04398742v1>`__
diff --git a/docs/source/sinr.text.rst b/docs/source/sinr.text.rst
index 3f2de04..0e51a6a 100644
--- a/docs/source/sinr.text.rst
+++ b/docs/source/sinr.text.rst
@@ -33,6 +33,14 @@ Preprocess Text
    :members:
    :undoc-members:
    :show-inheritance:
+   
+Evaluate
+---------------------------
+
+.. automodule:: sinr.text.evaluate
+   :members:
+   :undoc-members:
+   :show-inheritance:
 
 Module contents
 ---------------
diff --git a/notebooks/TransfertExample.ipynb b/notebooks/TransfertExample.ipynb
new file mode 100644
index 0000000..1158cb4
--- /dev/null
+++ b/notebooks/TransfertExample.ipynb
@@ -0,0 +1,855 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f38ae951-486e-4a47-9eac-af96a4bff6d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8ccf10dc-c324-4146-9801-e2a7685a0ae2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "\t\t\t<script type=\"text/javascript\">\n",
+       "\t\t\t<!--\n",
+       "\t\t\t\t\n",
+       "\t\t\t{\n",
+       "\t\t\t\tvar element = document.getElementById('NetworKit_script');\n",
+       "\t\t\t\tif (element) {\n",
+       "\t\t\t\t\telement.parentNode.removeChild(element);\n",
+       "\t\t\t\t}\n",
+       "\t\t\t\telement = document.createElement('script');\n",
+       "\t\t\t\telement.type = 'text/javascript';\n",
+       "\t\t\t\telement.innerHTML = 'function NetworKit_pageEmbed(id) { var i, j; var elements; elements = document.getElementById(id).getElementsByClassName(\"Plot\"); for (i=0; i<elements.length; i++) { elements[i].id = id + \"_Plot_\" + i; var data = elements[i].getAttribute(\"data-image\").split(\"|\"); elements[i].removeAttribute(\"data-image\"); var content = \"<div class=\\\\\"Image\\\\\" id=\\\\\"\" + elements[i].id + \"_Image\\\\\" />\"; elements[i].innerHTML = content; elements[i].setAttribute(\"data-image-index\", 0); elements[i].setAttribute(\"data-image-length\", data.length); for (j=0; j<data.length; j++) { elements[i].setAttribute(\"data-image-\" + j, data[j]); } NetworKit_plotUpdate(elements[i]); elements[i].onclick = function (e) { NetworKit_overlayShow((e.target) ? e.target : e.srcElement); } } elements = document.getElementById(id).getElementsByClassName(\"HeatCell\"); for (i=0; i<elements.length; i++) { var data = parseFloat(elements[i].getAttribute(\"data-heat\")); var color = \"#00FF00\"; if (data <= 1 && data > 0) { color = \"hsla(0, 100%, 75%, \" + (data) + \")\"; } else if (data <= 0 && data >= -1) { color = \"hsla(240, 100%, 75%, \" + (-data) + \")\"; } elements[i].style.backgroundColor = color; } elements = document.getElementById(id).getElementsByClassName(\"Details\"); for (i=0; i<elements.length; i++) { elements[i].setAttribute(\"data-title\", \"-\"); NetworKit_toggleDetails(elements[i]); elements[i].onclick = function (e) { NetworKit_toggleDetails((e.target) ? e.target : e.srcElement); } } elements = document.getElementById(id).getElementsByClassName(\"MathValue\"); for (i=elements.length-1; i>=0; i--) { value = elements[i].innerHTML.trim(); if (value === \"nan\") { elements[i].parentNode.innerHTML = \"\" } } elements = document.getElementById(id).getElementsByClassName(\"SubCategory\"); for (i=elements.length-1; i>=0; i--) { value = elements[i].innerHTML.trim(); if (value === \"\") { elements[i].parentNode.removeChild(elements[i]) } } elements = document.getElementById(id).getElementsByClassName(\"Category\"); for (i=elements.length-1; i>=0; i--) { value = elements[i].innerHTML.trim(); if (value === \"\") { elements[i].parentNode.removeChild(elements[i]) } } var isFirefox = false; try { isFirefox = typeof InstallTrigger !== \"undefined\"; } catch (e) {} if (!isFirefox) { alert(\"Currently the function\\'s output is only fully supported by Firefox.\"); } } function NetworKit_plotUpdate(source) { var index = source.getAttribute(\"data-image-index\"); var data = source.getAttribute(\"data-image-\" + index); var image = document.getElementById(source.id + \"_Image\"); image.style.backgroundImage = \"url(\" + data + \")\"; } function NetworKit_showElement(id, show) { var element = document.getElementById(id); element.style.display = (show) ? \"block\" : \"none\"; } function NetworKit_overlayShow(source) { NetworKit_overlayUpdate(source); NetworKit_showElement(\"NetworKit_Overlay\", true); } function NetworKit_overlayUpdate(source) { document.getElementById(\"NetworKit_Overlay_Title\").innerHTML = source.title; var index = source.getAttribute(\"data-image-index\"); var data = source.getAttribute(\"data-image-\" + index); var image = document.getElementById(\"NetworKit_Overlay_Image\"); image.setAttribute(\"data-id\", source.id); image.style.backgroundImage = \"url(\" + data + \")\"; var link = document.getElementById(\"NetworKit_Overlay_Toolbar_Bottom_Save\"); link.href = data; link.download = source.title + \".svg\"; } function NetworKit_overlayImageShift(delta) { var image = document.getElementById(\"NetworKit_Overlay_Image\"); var source = document.getElementById(image.getAttribute(\"data-id\")); var index = parseInt(source.getAttribute(\"data-image-index\")); var length = parseInt(source.getAttribute(\"data-image-length\")); var index = (index+delta) % length; if (index < 0) { index = length + index; } source.setAttribute(\"data-image-index\", index); NetworKit_overlayUpdate(source); } function NetworKit_toggleDetails(source) { var childs = source.children; var show = false; if (source.getAttribute(\"data-title\") == \"-\") { source.setAttribute(\"data-title\", \"+\"); show = false; } else { source.setAttribute(\"data-title\", \"-\"); show = true; } for (i=0; i<childs.length; i++) { if (show) { childs[i].style.display = \"block\"; } else { childs[i].style.display = \"none\"; } } }';\n",
+       "\t\t\t\telement.setAttribute('id', 'NetworKit_script');\n",
+       "\t\t\t\tdocument.head.appendChild(element);\n",
+       "\t\t\t}\n",
+       "\t\t\n",
+       "\t\t\t\t\n",
+       "\t\t\t{\n",
+       "\t\t\t\tvar element = document.getElementById('NetworKit_style');\n",
+       "\t\t\t\tif (element) {\n",
+       "\t\t\t\t\telement.parentNode.removeChild(element);\n",
+       "\t\t\t\t}\n",
+       "\t\t\t\telement = document.createElement('style');\n",
+       "\t\t\t\telement.type = 'text/css';\n",
+       "\t\t\t\telement.innerHTML = '.NetworKit_Page { font-family: Arial, Helvetica, sans-serif; font-size: 14px; } .NetworKit_Page .Value:before { font-family: Arial, Helvetica, sans-serif; font-size: 1.05em; content: attr(data-title) \":\"; margin-left: -2.5em; padding-right: 0.5em; } .NetworKit_Page .Details .Value:before { display: block; } .NetworKit_Page .Value { font-family: monospace; white-space: pre; padding-left: 2.5em; white-space: -moz-pre-wrap !important; white-space: -pre-wrap; white-space: -o-pre-wrap; white-space: pre-wrap; word-wrap: break-word; tab-size: 4; -moz-tab-size: 4; } .NetworKit_Page .Category { clear: both; padding-left: 1em; margin-bottom: 1.5em; } .NetworKit_Page .Category:before { content: attr(data-title); font-size: 1.75em; display: block; margin-left: -0.8em; margin-bottom: 0.5em; } .NetworKit_Page .SubCategory { margin-bottom: 1.5em; padding-left: 1em; } .NetworKit_Page .SubCategory:before { font-size: 1.6em; display: block; margin-left: -0.8em; margin-bottom: 0.5em; } .NetworKit_Page .SubCategory[data-title]:before { content: attr(data-title); } .NetworKit_Page .Block { display: block; } .NetworKit_Page .Block:after { content: \".\"; visibility: hidden; display: block; height: 0; clear: both; } .NetworKit_Page .Block .Thumbnail_Overview, .NetworKit_Page .Block .Thumbnail_ScatterPlot { width: 260px; float: left; } .NetworKit_Page .Block .Thumbnail_Overview img, .NetworKit_Page .Block .Thumbnail_ScatterPlot img { width: 260px; } .NetworKit_Page .Block .Thumbnail_Overview:before, .NetworKit_Page .Block .Thumbnail_ScatterPlot:before { display: block; text-align: center; font-weight: bold; } .NetworKit_Page .Block .Thumbnail_Overview:before { content: attr(data-title); } .NetworKit_Page .HeatCell { font-family: \"Courier New\", Courier, monospace; cursor: pointer; } .NetworKit_Page .HeatCell, .NetworKit_Page .HeatCellName { display: inline; padding: 0.1em; margin-right: 2px; background-color: #FFFFFF } .NetworKit_Page .HeatCellName { margin-left: 0.25em; } .NetworKit_Page .HeatCell:before { content: attr(data-heat); display: inline-block; color: #000000; width: 4em; text-align: center; } .NetworKit_Page .Measure { clear: both; } .NetworKit_Page .Measure .Details { cursor: pointer; } .NetworKit_Page .Measure .Details:before { content: \"[\" attr(data-title) \"]\"; display: block; } .NetworKit_Page .Measure .Details .Value { border-left: 1px dotted black; margin-left: 0.4em; padding-left: 3.5em; pointer-events: none; } .NetworKit_Page .Measure .Details .Spacer:before { content: \".\"; opacity: 0.0; pointer-events: none; } .NetworKit_Page .Measure .Plot { width: 440px; height: 440px; cursor: pointer; float: left; margin-left: -0.9em; margin-right: 20px; } .NetworKit_Page .Measure .Plot .Image { background-repeat: no-repeat; background-position: center center; background-size: contain; height: 100%; pointer-events: none; } .NetworKit_Page .Measure .Stat { width: 500px; float: left; } .NetworKit_Page .Measure .Stat .Group { padding-left: 1.25em; margin-bottom: 0.75em; } .NetworKit_Page .Measure .Stat .Group .Title { font-size: 1.1em; display: block; margin-bottom: 0.3em; margin-left: -0.75em; border-right-style: dotted; border-right-width: 1px; border-bottom-style: dotted; border-bottom-width: 1px; background-color: #D0D0D0; padding-left: 0.2em; } .NetworKit_Page .Measure .Stat .Group .List { -webkit-column-count: 3; -moz-column-count: 3; column-count: 3; } .NetworKit_Page .Measure .Stat .Group .List .Entry { position: relative; line-height: 1.75em; } .NetworKit_Page .Measure .Stat .Group .List .Entry[data-tooltip]:before { position: absolute; left: 0; top: -40px; background-color: #808080; color: #ffffff; height: 30px; line-height: 30px; border-radius: 5px; padding: 0 15px; content: attr(data-tooltip); white-space: nowrap; display: none; } .NetworKit_Page .Measure .Stat .Group .List .Entry[data-tooltip]:after { position: absolute; left: 15px; top: -10px; border-top: 7px solid #808080; border-left: 7px solid transparent; border-right: 7px solid transparent; content: \"\"; display: none; } .NetworKit_Page .Measure .Stat .Group .List .Entry[data-tooltip]:hover:after, .NetworKit_Page .Measure .Stat .Group .List .Entry[data-tooltip]:hover:before { display: block; } .NetworKit_Page .Measure .Stat .Group .List .Entry .MathValue { font-family: \"Courier New\", Courier, monospace; } .NetworKit_Page .Measure:after { content: \".\"; visibility: hidden; display: block; height: 0; clear: both; } .NetworKit_Page .PartitionPie { clear: both; } .NetworKit_Page .PartitionPie img { width: 600px; } #NetworKit_Overlay { left: 0px; top: 0px; display: none; position: absolute; width: 100%; height: 100%; background-color: rgba(0,0,0,0.6); z-index: 1000; } #NetworKit_Overlay_Title { position: absolute; color: white; transform: rotate(-90deg); width: 32em; height: 32em; padding-right: 0.5em; padding-top: 0.5em; text-align: right; font-size: 40px; } #NetworKit_Overlay .button { background: white; cursor: pointer; } #NetworKit_Overlay .button:before { size: 13px; display: inline-block; text-align: center; margin-top: 0.5em; margin-bottom: 0.5em; width: 1.5em; height: 1.5em; } #NetworKit_Overlay .icon-close:before { content: \"X\"; } #NetworKit_Overlay .icon-previous:before { content: \"P\"; } #NetworKit_Overlay .icon-next:before { content: \"N\"; } #NetworKit_Overlay .icon-save:before { content: \"S\"; } #NetworKit_Overlay_Toolbar_Top, #NetworKit_Overlay_Toolbar_Bottom { position: absolute; width: 40px; right: 13px; text-align: right; z-index: 1100; } #NetworKit_Overlay_Toolbar_Top { top: 0.5em; } #NetworKit_Overlay_Toolbar_Bottom { Bottom: 0.5em; } #NetworKit_Overlay_ImageContainer { position: absolute; top: 5%; left: 5%; height: 90%; width: 90%; background-repeat: no-repeat; background-position: center center; background-size: contain; } #NetworKit_Overlay_Image { height: 100%; width: 100%; background-repeat: no-repeat; background-position: center center; background-size: contain; }';\n",
+       "\t\t\t\telement.setAttribute('id', 'NetworKit_style');\n",
+       "\t\t\t\tdocument.head.appendChild(element);\n",
+       "\t\t\t}\n",
+       "\t\t\n",
+       "\t\t\t\t\n",
+       "\t\t\t{\n",
+       "\t\t\t\tvar element = document.getElementById('NetworKit_Overlay');\n",
+       "\t\t\t\tif (element) {\n",
+       "\t\t\t\t\telement.parentNode.removeChild(element);\n",
+       "\t\t\t\t}\n",
+       "\t\t\t\telement = document.createElement('div');\n",
+       "\t\t\t\telement.innerHTML = '<div id=\"NetworKit_Overlay_Toolbar_Top\"><div class=\"button icon-close\" id=\"NetworKit_Overlay_Close\" /></div><div id=\"NetworKit_Overlay_Title\" /> <div id=\"NetworKit_Overlay_ImageContainer\"> <div id=\"NetworKit_Overlay_Image\" /> </div> <div id=\"NetworKit_Overlay_Toolbar_Bottom\"> <div class=\"button icon-previous\" onclick=\"NetworKit_overlayImageShift(-1)\" /> <div class=\"button icon-next\" onclick=\"NetworKit_overlayImageShift(1)\" /> <a id=\"NetworKit_Overlay_Toolbar_Bottom_Save\"><div class=\"button icon-save\" /></a> </div>';\n",
+       "\t\t\t\telement.setAttribute('id', 'NetworKit_Overlay');\n",
+       "\t\t\t\tdocument.body.appendChild(element);\n",
+       "\t\t\t\tdocument.getElementById('NetworKit_Overlay_Close').onclick = function (e) {\n",
+       "\t\t\t\t\tdocument.getElementById('NetworKit_Overlay').style.display = 'none';\n",
+       "\t\t\t\t}\n",
+       "\t\t\t}\n",
+       "\t\t\n",
+       "\t\t\t-->\n",
+       "\t\t\t</script>\n",
+       "\t\t"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/lium/buster1/dugue/miniconda3-2023/envs/sinr-dev/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "2024-07-19 17:48:01,117 - load_from_cooc_pkl - INFO - Building Graph.\n",
+      "2024-07-19 17:48:01,118 - load_pkl_text - INFO - Loading cooccurrence matrix and dictionary.\n",
+      "2024-07-19 17:48:01,152 - load_pkl_text - INFO - Finished loading data.\n",
+      "2024-07-19 17:48:03,631 - load_from_cooc_pkl - INFO - Finished building graph.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import sinr.graph_embeddings as ge\n",
+    "import sinr.text.evaluate as ev\n",
+    "#Subsample of OANC corpus as a co-occurrence matrix\n",
+    "sinr = ge.SINr.load_from_cooc_pkl(\"oanc_extracted_min_freq20_max_freq5900_prct_sampling1_matrix.pkl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a3ce6ca7-a4b9-4539-8850-09829157afc3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(17706, 'words of vocabulary in this subsample')"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(sinr.wrd_to_idx), \"words of vocabulary in this subsample\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ff36b06d-a6f7-487e-84bb-481d8065dfb6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-07-19 17:48:03,755 - detect_communities - INFO - Detecting communities.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Gamma for louvain : 80\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-07-19 17:48:04,714 - detect_communities - INFO - Finished detecting communities.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Communities detected in 0.90354 [s]\n",
+      "solution properties:\n",
+      "-------------------  ------------\n",
+      "# communities        4933\n",
+      "min community size      1\n",
+      "max community size     32\n",
+      "avg. community size     3.5893\n",
+      "modularity              0.0345125\n",
+      "-------------------  ------------\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<networkit.structures.Partition at 0x7f6c4dc89ad0>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sinr.detect_communities(gamma=80)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "903e3116-25e3-4feb-a4d8-521732aef5bf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-07-19 17:48:04,767 - extract_embeddings - INFO - Extracting embeddings.\n",
+      "2024-07-19 17:48:04,767 - extract_embeddings - INFO - Applying NFM.\n",
+      "2024-07-19 17:48:04,769 - get_nfm_embeddings - INFO - Starting NFM\n",
+      "2024-07-19 17:48:30,492 - extract_embeddings - INFO - NFM successfully applied.\n",
+      "2024-07-19 17:48:30,494 - extract_embeddings - INFO - Finished extracting embeddings.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sinr.extract_embeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c36d77c4-9bed-484b-8933-f3b80c87d626",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                      \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "94 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                    \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "27 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                      "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "235 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'MEN': 0.46094523263674375,\n",
+       " 'WS353': 0.4636897182566408,\n",
+       " 'SCWS': 0.42946339109424253}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele = ge.InterpretableWordsModelBuilder(sinr, \"modele\", n_jobs=8, n_neighbors=4).build()\n",
+    "ev.similarity_MEN_WS353_SCWS(modele)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "14fa05a2-a6f2-4f1c-be06-45a0868fe538",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((17706, 4933), '(nb of words, dimensions)')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele.vectors.shape, \"(nb of words, dimensions)\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c315614c-fa14-4c3f-bcfe-1315e762f25f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-07-19 17:48:39,768 - load_from_cooc_pkl - INFO - Building Graph.\n",
+      "2024-07-19 17:48:39,768 - load_pkl_text - INFO - Loading cooccurrence matrix and dictionary.\n",
+      "2024-07-19 17:48:39,787 - load_pkl_text - INFO - Finished loading data.\n",
+      "2024-07-19 17:48:41,251 - load_from_cooc_pkl - INFO - Finished building graph.\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Small Subsample of OANC corpus as a co-occurrence matrix\n",
+    "sinr_small = ge.SINr.load_from_cooc_pkl(\"oanc_extracted_min_freq50_max_freq3000_prct_sampling08_matrix.pkl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f06e8450-0489-41fe-b026-3ff891d75e8a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(9494, 'words of vocabulary')"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(sinr_small.wrd_to_idx), \"words of vocabulary\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "63bbbfa5-5ead-46d3-9911-635b10a60243",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(8212, 'words are present in the big subsample, but absent in the small one')"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(sinr.wrd_to_idx) - len(sinr_small.wrd_to_idx), \"words are present in the big subsample, but absent in the small one\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "5abeefd5-4a8f-48e3-925f-80ff3bbc6a67",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Transferring the communities of the bigger model to the small one\n",
+    "sinr_small.transfert_communities_labels(modele.get_communities_as_labels_sets())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "06808028-4389-4af3-99c0-d35a815ba5d2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2024-07-19 17:48:41,443 - extract_embeddings - INFO - Extracting embeddings.\n",
+      "2024-07-19 17:48:41,443 - extract_embeddings - INFO - Applying NFM.\n",
+      "2024-07-19 17:48:41,445 - get_nfm_embeddings - INFO - Starting NFM\n",
+      "2024-07-19 17:48:56,453 - extract_embeddings - INFO - NFM successfully applied.\n",
+      "2024-07-19 17:48:56,454 - extract_embeddings - INFO - Finished extracting embeddings.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sinr_small.extract_embeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "b9a8fccd-d4db-43a5-9dbd-0031a00c08e9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                      \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "205 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                    \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "86 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "                                                                      "
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "482 missing words\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\r"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'MEN': 0.3092365066427464,\n",
+       " 'WS353': 0.37938716672217637,\n",
+       " 'SCWS': 0.3762601899389452}"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small = ge.InterpretableWordsModelBuilder(sinr_small, \"modele\", n_jobs=8, n_neighbors=4).build()\n",
+    "ev.similarity_MEN_WS353_SCWS(modele_small)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "164a049b-cc48-4798-9a53-b8cc2793b1a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "('Small model : ', (9494, 4700), '(nb of words, dimensions)')"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"Small model : \", modele_small.vectors.shape, \"(nb of words, dimensions)\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "68946821-0157-4e6a-807a-a00040cc962a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "('Big modele : ', (17706, 4933), '(nb of words, dimensions)')"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"Big modele : \", modele.vectors.shape, \"(nb of words, dimensions)\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2be5f6b1-4c51-43b6-8071-5e78f842addc",
+   "metadata": {},
+   "source": [
+    "### Interpreting the small model in the big one's referential\n",
+    "\n",
+    "The small model and its projected version into the big one's referential have the same neighborings, but their neighboring may be different from the big one."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "2ea44036-bffd-4fc7-add8-34efb881070e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "modele_small_bigasaref = modele.get_vectors_using_self_space(modele_small)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "6bad3dda-bf1b-4f9b-9b5e-42120f3e3c7c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'object ': 'cheese',\n",
+       " 'neighbors ': [('bread', 0.37), ('wine', 0.35), ('bottle', 0.32)]}"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small_bigasaref.most_similar(\"cheese\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "aa0f8771-d871-4c22-a2ea-9e89849e9b52",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'object ': 'cheese',\n",
+       " 'neighbors ': [('bread', 0.37), ('wine', 0.35), ('bottle', 0.32)]}"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small.most_similar(\"cheese\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "bb693b80-d6b6-45f3-802f-9de397dd71b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'object ': 'cheese',\n",
+       " 'neighbors ': [('foodstuff', 0.49), ('sausage', 0.45), ('bread', 0.41)]}"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele.most_similar(\"cheese\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc020130-d66c-4693-8c45-4977c16907ad",
+   "metadata": {},
+   "source": [
+    "The small model and its projected version into the big one's referential have the same stereotypes, but the dimensions ids are different. The dimensions ids of the projected versions are aligned with the big model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "ec58906c-a556-4bcd-8115-5864af8734a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 769,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.23, 'hippocampus'),\n",
+       "   (0.22, 'amygdala'),\n",
+       "   (0.21, 'furrow')]},\n",
+       " {'dimension': 1968,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.38, 'tclr'), (0.1, 'spleen'), (0.09, 'intestine')]},\n",
+       " {'dimension': 1944,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.34, 'cord'), (0.32, 'l6-s1'), (0.3, 'spinal')]},\n",
+       " {'dimension': 1196,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.1, 'autistic'), (0.06, 'amyloid'), (0.06, 'amygdala')]},\n",
+       " {'dimension': 291,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.47, 'rdta'), (0.36, 'scid'), (0.3, 'balb')]}]"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele.get_obj_stereotypes(\"hippocampus\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "2543b046-e608-45e1-a4a2-1e3aa2e7ab14",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 1812,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.26, 'furrow'), (0.23, 'hippocampus'), (0.2, 'cortex')]},\n",
+       " {'dimension': 757,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.11, 'cirrhosis'), (0.11, 'intestine'), (0.09, 'spleen')]},\n",
+       " {'dimension': 1494,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.35, 'cord'), (0.29, 'spinal'), (0.28, 'dorsal')]},\n",
+       " {'dimension': 1673,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.03, 'hippocampus'), (0.03, 'lifelong'), (0.03, 'diet')]},\n",
+       " {'dimension': 2862,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.12, 'translocation'),\n",
+       "   (0.07, 'localization'),\n",
+       "   (0.07, 'chloroplast')]}]"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small.get_obj_stereotypes(\"hippocampus\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "d7097aeb-9e59-4f0f-a229-58b5a48d837b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 769,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.26, 'furrow'), (0.23, 'hippocampus'), (0.2, 'cortex')]},\n",
+       " {'dimension': 1968,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.11, 'cirrhosis'), (0.11, 'intestine'), (0.09, 'spleen')]},\n",
+       " {'dimension': 3455,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.03, 'hippocampus'), (0.03, 'lifelong'), (0.03, 'diet')]},\n",
+       " {'dimension': 1944,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.35, 'cord'), (0.29, 'spinal'), (0.28, 'dorsal')]},\n",
+       " {'dimension': 1670,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.12, 'phytoestrogen'), (0.1, 'rodent'), (0.1, 'pufa')]}]"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small_bigasaref.get_obj_stereotypes(\"hippocampus\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "235e87c1-6d7f-4cae-96d5-0539d6eb0d06",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 640,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.12, 'caloric'), (0.11, 'beverage'), (0.08, 'intake')]},\n",
+       " {'dimension': 641,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.1, 'beverage'), (0.08, 'alcoholic'), (0.08, 'foc')]},\n",
+       " {'dimension': 4784,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.18, 'overdominance'),\n",
+       "   (0.16, 'k1'),\n",
+       "   (0.11, 'phosphatidylinositol')]},\n",
+       " {'dimension': 713,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.1, 'bottled'), (0.05, 'gin'), (0.04, 'vodka')]},\n",
+       " {'dimension': 439,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.17, 'parenchyma'),\n",
+       "   (0.15, 'extravascular'),\n",
+       "   (0.13, 'artifactual')]}]"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele.get_obj_stereotypes(\"beverage\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "8d1883f7-5e87-4ba1-be06-6b3c20cb80e8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 2220,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.14, 'beverage'), (0.09, 'intake'), (0.06, 'calorie')]},\n",
+       " {'dimension': 183,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.11, 'beverage'), (0.07, 'alcoholic'), (0.02, 'citrus')]},\n",
+       " {'dimension': 1362,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.04, 'alcoholic'), (0.03, 'beverage'), (0.02, 'liquor')]},\n",
+       " {'dimension': 524,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.05, 'antioxidant'), (0.04, 'fortify'), (0.04, 'bottle')]},\n",
+       " {'dimension': 2511,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.07, 'adherent'),\n",
+       "   (0.07, 'emphysema'),\n",
+       "   (0.06, 'neutrophil')]}]"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small.get_obj_stereotypes(\"beverage\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "18193578-e3a1-4c37-a600-64ce76df0feb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'dimension': 640,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.14, 'beverage'), (0.09, 'intake'), (0.06, 'calorie')]},\n",
+       " {'dimension': 641,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.11, 'beverage'), (0.07, 'alcoholic'), (0.02, 'citrus')]},\n",
+       " {'dimension': 713,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.04, 'alcoholic'), (0.03, 'beverage'), (0.02, 'liquor')]},\n",
+       " {'dimension': 1618,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.05, 'antioxidant'), (0.04, 'fortify'), (0.04, 'bottle')]},\n",
+       " {'dimension': 439,\n",
+       "  'value': True,\n",
+       "  'stereotypes': [(0.07, 'adherent'),\n",
+       "   (0.07, 'emphysema'),\n",
+       "   (0.06, 'neutrophil')]}]"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "modele_small_bigasaref.get_obj_stereotypes(\"beverage\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6154d09c-56f5-4690-9125-90a996e41f1e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fa124f22-269f-438e-9725-f418055e6510",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "sinr-dev",
+   "language": "python",
+   "name": "sinr-dev"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/oanc_extracted_min_freq20_max_freq5900_prct_sampling1_matrix.pkl b/notebooks/oanc_extracted_min_freq20_max_freq5900_prct_sampling1_matrix.pkl
new file mode 100644
index 0000000..c5c1cd4
Binary files /dev/null and b/notebooks/oanc_extracted_min_freq20_max_freq5900_prct_sampling1_matrix.pkl differ
diff --git a/notebooks/oanc_extracted_min_freq50_max_freq3000_prct_sampling08_matrix.pkl b/notebooks/oanc_extracted_min_freq50_max_freq3000_prct_sampling08_matrix.pkl
new file mode 100644
index 0000000..552aaf7
Binary files /dev/null and b/notebooks/oanc_extracted_min_freq50_max_freq3000_prct_sampling08_matrix.pkl differ
diff --git a/pyproject.toml b/pyproject.toml
index 6f7eba3..aed3bd5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,7 +10,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "sinr"
-version = "v1.2.0"
+version = "v1.3.1"
 description = "Build word and graph embeddings based on community detection in graphs."
 authors = ["Thibault Prouteau <thibault.prouteau@univ-lemans.fr>", "Nicolas Dugue <nicolas.dugue@univ-lemans.fr>", " Simon Guillot <simon.guillot@univ-lemans.fr>", "Anthony Perez"]
 license = "CeCILL 2.1"
diff --git a/sinr/__init__.py b/sinr/__init__.py
index ea12dc6..80804bf 100644
--- a/sinr/__init__.py
+++ b/sinr/__init__.py
@@ -2,4 +2,4 @@
 
 __author__ = """Thibault Prouteau"""
 __email__ = 'thibault.prouteau@univ-lemans.fr'
-__version__ = 'v1.2.0'
+__version__ = 'v1.3.1'
diff --git a/sinr/graph_embeddings.py b/sinr/graph_embeddings.py
index c383cdf..5d119f9 100644
--- a/sinr/graph_embeddings.py
+++ b/sinr/graph_embeddings.py
@@ -648,6 +648,55 @@ def get_communities_as_labels_sets(self):
                 labels.add(self.vocab[u])
             labels_sets.append(labels)
         return labels_sets
+    
+    def get_matching_communities(self, sinr_vector):
+        """Get the matching between two partitions with common vocabularies
+        
+        :param sinr_vector: Small model (target)
+        :type sinr_vector: SINrVectors
+        
+        :returns: Lists. The first indicating, at each of its index corresponding to the community's index of the self object (src), its matching number in the parameter sinr_vector's communities (tgt) if it exists. The second indicating, at each of its index corresponding to the community's index of the object in parameter, its matching number in the self object.
+        :rtype: (list[int],list[int])
+        """
+        
+        src_communities = self.get_communities_as_labels_sets()
+        l = [-1] * len(src_communities)
+        tgt_communities = sinr_vector.get_communities_as_labels_sets()
+        for id_src, lab_set_src in enumerate(src_communities):
+            for id_tgt, lab_set_tgt in enumerate(tgt_communities):
+                if len(lab_set_src.intersection(lab_set_tgt)) > 0:
+                    l[id_src] = id_tgt
+        tgt_from_src = [-1] * len(tgt_communities)
+        for idx, val in enumerate(l):
+            tgt_from_src[val] = idx
+        
+        return l, tgt_from_src
+    
+    def get_vectors_using_self_space(self, sinr_vector):
+        """Transpose the vectors of the sinr_vector object in parameter in the embedding space of the self object, using matching communities
+        
+        :param sinr_vector: Small model (target)
+        :type sinr_vector: SINrVectors
+        
+        :returns: Copy of the self model (the big one) with vectors of the parameter (small one) transposed to its referential
+        :rtype: SINrVectors
+        """
+        from scipy.sparse import coo_matrix
+        
+        matching_st, matching_ts = self.get_matching_communities(sinr_vector)
+        
+        vectors = sinr_vector.vectors.tocoo()
+        row = vectors.row
+        data = vectors.data
+        col = [matching_ts[val] for val in vectors.col]
+    
+        matrix = coo_matrix((data, (row, col)), shape=(sinr_vector.vectors.shape[0], self.vectors.shape[1]))
+        
+        import copy
+        self_copy = copy.deepcopy(self)
+        self_copy.set_vectors(matrix.tocsr())
+        self_copy.vocab = sinr_vector.vocab
+        return self_copy
 
     def set_n_jobs(self, n_jobs):
         """Set the number of jobs.