allenai · dakinggg · Sep 30, 2023 · Aug 26, 2023 · Aug 26, 2023 · Aug 26, 2023
diff --git a/Dockerfile b/Dockerfile
@@ -18,7 +18,7 @@ WORKDIR /work
 COPY requirements.in .
 
 RUN pip install -r requirements.in
-RUN pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz
+RUN pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_sm-0.5.3.tar.gz
 RUN python -m spacy download en_core_web_sm
 RUN python -m spacy download en_core_web_md
 

diff --git a/README.md b/README.md
@@ -19,7 +19,7 @@ pip install scispacy
 to install a model (see our full selection of available models below), run a command like the following:
 
 ```bash
-pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz
+pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_sm-0.5.3.tar.gz
 ```
 
 Note: We strongly recommend that you use an isolated Python environment (such as virtualenv or conda) to install scispacy.
@@ -76,14 +76,14 @@ pip install CMD-V(to paste the copied URL)
 
 | Model          | Description       | Install URL
 |:---------------|:------------------|:----------|
-| en_core_sci_sm | A full spaCy pipeline for biomedical data with a ~100k vocabulary. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz)|
-| en_core_sci_md |  A full spaCy pipeline for biomedical data with a ~360k vocabulary and 50k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_md-0.5.1.tar.gz)|
-| en_core_sci_lg |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and 600k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_lg-0.5.1.tar.gz)|
-| en_core_sci_scibert |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and `allenai/scibert-base` as the transformer model. You may want to [use a GPU](https://spacy.io/usage#gpu) with this model. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_scibert-0.5.1.tar.gz)|
-| en_ner_craft_md|  A spaCy NER model trained on the CRAFT corpus.|[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_craft_md-0.5.1.tar.gz)|
-| en_ner_jnlpba_md | A spaCy NER model trained on the JNLPBA corpus.| [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_jnlpba_md-0.5.1.tar.gz)|
-| en_ner_bc5cdr_md |  A spaCy NER model trained on the BC5CDR corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_bc5cdr_md-0.5.1.tar.gz)|
-| en_ner_bionlp13cg_md |  A spaCy NER model trained on the BIONLP13CG corpus. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_bionlp13cg_md-0.5.1.tar.gz)|
+| en_core_sci_sm | A full spaCy pipeline for biomedical data with a ~100k vocabulary. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_sm-0.5.3.tar.gz)|
+| en_core_sci_md |  A full spaCy pipeline for biomedical data with a ~360k vocabulary and 50k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_md-0.5.3.tar.gz)|
+| en_core_sci_lg |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and 600k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_lg-0.5.3.tar.gz)|
+| en_core_sci_scibert |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and `allenai/scibert-base` as the transformer model. You may want to [use a GPU](https://spacy.io/usage#gpu) with this model. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_scibert-0.5.3.tar.gz)|
+| en_ner_craft_md|  A spaCy NER model trained on the CRAFT corpus.|[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_craft_md-0.5.3.tar.gz)|
+| en_ner_jnlpba_md | A spaCy NER model trained on the JNLPBA corpus.| [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_jnlpba_md-0.5.3.tar.gz)|
+| en_ner_bc5cdr_md |  A spaCy NER model trained on the BC5CDR corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_bc5cdr_md-0.5.3.tar.gz)|
+| en_ner_bionlp13cg_md |  A spaCy NER model trained on the BIONLP13CG corpus. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_bionlp13cg_md-0.5.3.tar.gz)|
 
 
 ## Additional Pipeline Components

diff --git a/RELEASE.md b/RELEASE.md
@@ -15,16 +15,11 @@ Update the version in version.py.
 
 #### Training new models
 
-For the release, new models should be trained using the `scripts/pipeline.sh` and `scripts/ner_pipeline.sh` scripts, for the small, medium and large models, and specialized NER models. Remember to export the `ONTONOTES_PATH` and `ONTONOTES_PERCENT` environment variables to mix in the ontonotes training data.
+The entire pipeline can be run using `spacy project run all`. This will train and package all the models.
 
-```
-bash scripts/pipeline.sh small
-bash scripts/pipeline.sh medium
-bash scripts/pipeline.sh large
-bash scripts/ner_pipeline.sh <path to medium base model>
-```
+The packages should then be uploaded to the `https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/{VERSION}` S3 bucket, and references to previous models (e.g in the readme and in the docs) should be updated. You can find all these places using `git grep <previous version>`.
 
-these should then be uploaded to the `https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/{VERSION}` S3 bucket, and references to previous models (e.g in the readme and in the docs) should be updated. You can find all these places using `git grep <previous version>`.
+The scripts `install_local_packages.py`, `instal_remote_packages.py`, `print_out_metrics.py`, `smoke_test.py`, and `uninstall_local_packages.py` are useful for testing at each step of the process. Before uploading, `install_local_packages.py` and `smoke_test.py` can be used to make sure the packages are installable and do a quick check of output. `print_out_metrics.py` can then be used to easily get the metrics that need to be update in the README. Once the packages have been uploaded, `uninstall_local_packages.py`, `install_remote_packages.py`, and `smoke_test.py` can be used to ensure everything was uploaded correctly.
 
 #### Merge a PR with the above changes
 Merge a PR with the above changes, and publish a release with a tag corresponding to the commit from the merged PR. This should trigger the publish github action, which will create the `scispacy` package and publish it to pypi.

diff --git a/configs/base_ner.cfg b/configs/base_ner.cfg
@@ -48,8 +48,8 @@ nO = null
 [components.ner.model.tok2vec.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
 width = 96
-attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE", "SPACY"]
-rows = [5000, 2500, 2500, 2500, 100]
+attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
+rows = [5000, 1000, 2500, 2500]
 include_static_vectors = ${vars.include_static_vectors}
 
 [components.ner.model.tok2vec.encode]

diff --git a/configs/base_ner_scibert.cfg b/configs/base_ner_scibert.cfg
@@ -45,8 +45,8 @@ nO = null
 [components.ner.model.tok2vec.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
 width = 96
-attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE", "SPACY"]
-rows = [5000, 2500, 2500, 2500, 100]
+attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
+rows = [5000, 1000, 2500, 2500]
 include_static_vectors = false
 
 [components.ner.model.tok2vec.encode]

diff --git a/configs/base_parser_tagger.cfg b/configs/base_parser_tagger.cfg
@@ -73,8 +73,8 @@ factory = "tok2vec"
 [components.tok2vec.model.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
 width = ${components.tok2vec.model.encode.width}
-attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE", "SPACY"]
-rows = [5000, 2500, 2500, 2500, 100]
+attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE", "SPACY", "IS_SPACE"]
+rows = [5000, 1000, 2500, 2500, 50, 50]
 include_static_vectors = ${vars.include_static_vectors}
 
 [components.tok2vec.model.encode]

diff --git a/docs/index.md b/docs/index.md
@@ -17,14 +17,14 @@ pip install <Model URL>
 
 | Model          | Description       | Install URL
 |:---------------|:------------------|:----------|
-| en_core_sci_sm | A full spaCy pipeline for biomedical data. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz)|
-| en_core_sci_md |  A full spaCy pipeline for biomedical data with a larger vocabulary and 50k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_md-0.5.1.tar.gz)|
-| en_core_sci_scibert |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and `allenai/scibert-base` as the transformer model. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_scibert-0.5.1.tar.gz)|
-| en_core_sci_lg |  A full spaCy pipeline for biomedical data with a larger vocabulary and 600k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_lg-0.5.1.tar.gz)|
-| en_ner_craft_md|  A spaCy NER model trained on the CRAFT corpus.|[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_craft_md-0.5.1.tar.gz)|
-| en_ner_jnlpba_md | A spaCy NER model trained on the JNLPBA corpus.| [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_jnlpba_md-0.5.1.tar.gz)|
-| en_ner_bc5cdr_md |  A spaCy NER model trained on the BC5CDR corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_bc5cdr_md-0.5.1.tar.gz)|
-| en_ner_bionlp13cg_md |  A spaCy NER model trained on the BIONLP13CG corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_ner_bionlp13cg_md-0.5.1.tar.gz)|
+| en_core_sci_sm | A full spaCy pipeline for biomedical data. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_sm-0.5.3.tar.gz)|
+| en_core_sci_md |  A full spaCy pipeline for biomedical data with a larger vocabulary and 50k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_md-0.5.3.tar.gz)|
+| en_core_sci_scibert |  A full spaCy pipeline for biomedical data with a ~785k vocabulary and `allenai/scibert-base` as the transformer model. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_scibert-0.5.3.tar.gz)|
+| en_core_sci_lg |  A full spaCy pipeline for biomedical data with a larger vocabulary and 600k word vectors. |[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_core_sci_lg-0.5.3.tar.gz)|
+| en_ner_craft_md|  A spaCy NER model trained on the CRAFT corpus.|[Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_craft_md-0.5.3.tar.gz)|
+| en_ner_jnlpba_md | A spaCy NER model trained on the JNLPBA corpus.| [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_jnlpba_md-0.5.3.tar.gz)|
+| en_ner_bc5cdr_md |  A spaCy NER model trained on the BC5CDR corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_bc5cdr_md-0.5.3.tar.gz)|
+| en_ner_bionlp13cg_md |  A spaCy NER model trained on the BIONLP13CG corpus. | [Download](https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/en_ner_bionlp13cg_md-0.5.3.tar.gz)|
 
 
 
@@ -34,18 +34,18 @@ Our models achieve performance within 3% of published state of the art dependenc
 
 | model          | UAS | LAS   | POS   | Mentions (F1) | Web UAS | 
 |:---------------|:----|:------|:------|:---|:---|
-| en_core_sci_sm | 89.03| 87.00  |  98.13  |  67.87  |  87.42  |
-| en_core_sci_md | 89.73| 87.85 |  98.40 |  69.53 |  87.79  |
-| en_core_sci_lg | 89.75| 87.79  |  98.49  |  69.69  |  87.74  |
-| en_core_sci_scibert | 92.21| 90.65  |  98.86  |  68.01  |  92.58  |
+| en_core_sci_sm | 89.39| 87.41  |  98.32  |  68.00  |  87.65  |
+| en_core_sci_md | 90.23| 88.39 |  98.39 |  68.95 |  87.63  |
+| en_core_sci_lg | 89.98| 88.15  |  98.50  |  68.67  |  88.21  |
+| en_core_sci_scibert | 92.54| 91.02  |  98.89  |  67.90  |  92.85  |
 
 
 | model          | F1 |   Entity Types|
 |:---------------|:-----|:--------|
-| en_ner_craft_md | 76.75|GGP, SO, TAXON, CHEBI, GO, CL|
-| en_ner_jnlpba_md | 72.28| DNA, CELL_TYPE, CELL_LINE, RNA, PROTEIN |
-| en_ner_bc5cdr_md | 84.53| DISEASE, CHEMICAL|
-| en_ner_bionlp13cg_md | 76.57| AMINO_ACID, ANATOMICAL_SYSTEM, CANCER, CELL, CELLULAR_COMPONENT, DEVELOPING_ANATOMICAL_STRUCTURE, GENE_OR_GENE_PRODUCT, IMMATERIAL_ANATOMICAL_ENTITY, MULTI-TISSUE_STRUCTURE, ORGAN, ORGANISM, ORGANISM_SUBDIVISION, ORGANISM_SUBSTANCE, PATHOLOGICAL_FORMATION, SIMPLE_CHEMICAL, TISSUE |
+| en_ner_craft_md | 77.56|GGP, SO, TAXON, CHEBI, GO, CL|
+| en_ner_jnlpba_md | 72.98| DNA, CELL_TYPE, CELL_LINE, RNA, PROTEIN |
+| en_ner_bc5cdr_md | 84.23| DISEASE, CHEMICAL|
+| en_ner_bionlp13cg_md | 77.36| AMINO_ACID, ANATOMICAL_SYSTEM, CANCER, CELL, CELLULAR_COMPONENT, DEVELOPING_ANATOMICAL_STRUCTURE, GENE_OR_GENE_PRODUCT, IMMATERIAL_ANATOMICAL_ENTITY, MULTI-TISSUE_STRUCTURE, ORGAN, ORGANISM, ORGANISM_SUBDIVISION, ORGANISM_SUBSTANCE, PATHOLOGICAL_FORMATION, SIMPLE_CHEMICAL, TISSUE |
 
 
 ### Example Usage

diff --git a/project.yml b/project.yml
@@ -2,7 +2,7 @@ title: "scispaCy pipeline"
 description: "All the steps needed in the scispaCy pipeline"
 
 vars:
-  version_string: "0.5.2"
+  version_string: "0.5.3"
   gpu_id: 0
   freqs_loc_s3: "s3://ai2-s2-scispacy/data/gorc_subset.freqs"
   freqs_loc_local: "assets/gorc_subset.freqs"

diff --git a/requirements.in b/requirements.in
@@ -1,5 +1,6 @@
 numpy
-spacy>=3.4.0,<3.5.0
+scipy<1.11
+spacy>=3.6.0,<3.7.0
 spacy-lookups-data
 pandas
 requests>=2.0.0,<3.0.0

diff --git a/scispacy/version.py b/scispacy/version.py
@@ -1,6 +1,6 @@
 _MAJOR = "0"
 _MINOR = "5"
-_REVISION = "2"
+_REVISION = "3"
 
 VERSION_SHORT = "{0}.{1}".format(_MAJOR, _MINOR)
 VERSION = "{0}.{1}.{2}".format(_MAJOR, _MINOR, _REVISION)
diff --git a/scripts/install_remote_packages.py b/scripts/install_remote_packages.py
@@ -4,7 +4,7 @@
 
 
 def main():
-    s3_prefix = "https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/"
+    s3_prefix = "https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.3/"
     model_names = [
         "en_core_sci_sm",
         "en_core_sci_md",

diff --git a/setup.py b/setup.py
@@ -41,7 +41,8 @@
     packages=find_packages(exclude=["*.tests", "*.tests.*", "tests.*", "tests"]),
     license="Apache",
     install_requires=[
-        "spacy>=3.4.0,<3.5.0",
+        "spacy>=3.6.0,<3.7.0",
+        "scipy<1.11",
         "requests>=2.0.0,<3.0.0",
         "conllu",
         "numpy",