NSpM

KO | EN

gitlite — search

#react #typescript #machine-learning #deep-learning #docker #java #windows #awesome #vue #awesome-list #pytorch #security #mcp #ios

(★ 225)

🤖 Neural SPARQL Machines for Knowledge Graph Question Answering.

File Explorer

Download Latest Version (.zip)

- - dbpedia-201610-manual-annotation.csv
  - dbpedia-201610-place-properties.csv
  - dbpedia-201610-properties.tsv
  - dbpedia-ontology-properties.tsv
- - Annotations_F30_art.csv
  - dbpedia-201610-place.csv
  - LC-QuAD_v6_art.csv
  - LC-QuAD_v6_other.csv
  - LC-QuAD_v6_personal.csv
  - LC-QuAD_v6_sport.csv
  - LC-QuAD_v6_sport_art.csv
  - QALD-7.csv
- - .DS_Store
  - composite_template.py
  - decision_tree.py
  - delete_lines.py
  - entity_errors.py
  - error_analysis.py
  - final_formatting.py
  - get_metadata.py
  - get_properties.py
  - GS_with_mve.csv
  - integrate.py
  - log_place
  - metadata_place.txt
  - PIPELINE
  - place_labels
  - range_place.py
  - README.md
  - remove_en.py
  - script.py
  - script2.py
  - sparql_generator.csv
  - sparql_generator.py
  - temp.py
  - tempout
  - test.txt
  - test_comp.csv
  - training_log
- - PIPELINE.md
  - readme.md
- __init__.py
- analyse.py
- data_gen.py
- filter_dataset.py
- generator.py
- generator_test.py
- generator_utils.py
- interpreter.py
- learner.py
- nmt.py
- prepare_dataset.py
- split_in_train_dev_test.py
- interpreter_airml_test.py
.gitattributes
.gitignore
CITATION.cff
LICENSE
README.md
requirements.txt

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# 🤖 Neural SPARQL Machines

[![Python 3.11](https://img.shields.io/badge/python-3.11-blue.svg)](https://www.python.org/downloads/release/python-3110/)

A Machine-Translation Approach for Question Answering over Knowledge Graphs.

![What does a NSpM do?](http://www.liberai.org/images/NSpM-image.png "What does a NSpM do?")

## IMPORTANT

If you are looking for the code for papers _"SPARQL as a Foreign Language"_ and _"Neural Machine Translation for Query Construction and Composition"_ please checkout tag [v0.1.0-akaha](https://github.com/LiberAI/NSpM/tree/v0.1.0-akaha) or branch [v1](https://github.com/LiberAI/NSpM/tree/v1).

## Local setup

Clone the repository.

```bash
pip install -r requirements.txt
```

## Example of usage

### The Generator module

#### Pre-generated data

You can extract pre-generated data and model checkpoints from [here](https://nspm-models.s3.eu-west-2.amazonaws.com/v2/art_30.zip) (1.1 GB) in folders having the respective names.

#### Manual Generation (Alternative to using pre-generated data)

The template used in the paper can be found in a file such as `Annotations_F30_art.csv`. `data/art_30` will be the ID of the working dataset used throughout the tutorial. To generate the training data, launch the following command.

```bash
mkdir -p data/art_30
python nspm/generator.py --templates data/templates/Annotations_F30_art.csv --output data/art_30
```

Launch the command if you want to build dataset seprately else it will internally be called while training.

```bash
python nspm/data_gen.py --input data/art_30 --output data/art_30
```

### The Learner module

Now go back to the initial directory and launch `learner.py` to train the model.

```bash
python nspm/learner.py --input data/art_30 --output data/art_30
```

This command will create a model checkpoints in `data/art_30` and some pickle files in `data/art_30/pickle_objects`.

### The Interpreter module

Predict the SPARQL query for a given question it will store the detailed output in output_query.

```bash
python nspm/interpreter.py --input data/art_30 --query "yuncken freeman has architected in how many cities?"
```
or, if you want to use NSpM with [airml](https://github.com/sahandilshan/airML) to install pre-trained models, follow these steps,
1. Install airML latest version from [here](https://pypi.org/project/airML/)
2. Navigate to the table.kns [here](https://github.com/sahandilshan/KBox/blob/dev/kns/2.0/table.kns) and check if your model is listed in that file.
3. Then copy the name of that model and use it with the `interpreter.py` as follows
```bash
python interpreter.py --airml http://nspm.org/art --output data/art_30 --inputstr "yuncken freeman has architected in how many cities?"
```

## Use cases & integrations

* Components of the [Adam Medical platform](https://www.graphen.ai/products/mi_feature.html) partly developed by [Jose A. Alvarado](https://www.linkedin.com/in/josealvaradoguzman/) at Graphen (including a humanoid robot called Dr Adam), rely on NSpM technology.
* The [Telegram NSpM chatbot](https://github.com/AKSW/NSpM/wiki/NSpM-Telegram-Bot) offers an integration of NSpM with the Telegram messaging platform.
* The [Google Summer of Code](https://summerofcode.withgoogle.com/) program has supported several contributors to work on NSpM-backed project "[A neural question answering model for DBpedia](https://github.com/dbpedia/neural-qa)" since 2018.
* A [question answering system](https://github.com/qasim9872/question-answering-system) was implemented on top of NSpM by [Muhammad Qasim](https://github.com/qasim9872).

## Publications

### SPARQL as a Foreign Language (2017)

* arXiv: https://arxiv.org/abs/1708.07624

```
@inproceedings{soru-marx-2017,
    author = "Tommaso Soru and Edgard Marx and Diego Moussallem and Gustavo Publio and Andr\'e Valdestilhas and Diego Esteves and Ciro Baron Neto",
    title = "{SPARQL} as a Foreign Language",
    year = "2017",
    journal = "13th International Conference on Semantic Systems (SEMANTiCS 2017) - Posters and Demos",
    url = "https://arxiv.org/abs/1708.07624",
}
```

### Neural Machine Translation for Query Construction and Composition (2018)

* NAMPI Website: https://uclnlp.github.io/nampi/
* arXiv: https://arxiv.org/abs/1806.10478

```
@inproceedings{soru-marx-nampi2018,
    author = "Tommaso Soru and Edgard Marx and Andr\'e Valdestilhas and Diego Esteves and Diego Moussallem and Gustavo Publio",
    title = "Neural Machine Translation for Query Construction and Composition",
    year = "2018",
    journal = "ICML Workshop on Neural Abstract Machines \& Program Induction (NAMPI v2)",
    url = "https://arxiv.org/abs/1806.10478",
}
```

### Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition (2020)

* arXiv: https://arxiv.org/abs/2010.10900

```
@inproceedings{panchbhai-2020,
    author = "Anand Panchbhai and Tommaso Soru and Edgard Marx",
    title = "Exploring Sequence-to-Sequence Models for {SPARQL} Pattern Composition",
    year = "2020",
    journal = "First Indo-American Knowledge Graph and Semantic Web Conference",
    url = "https://arxiv.org/abs/2010.10900",
}
```

### Liber AI on Medium (2020)

* [What is a Neural SPARQL Machine?](https://medium.com/liber-ai/what-is-a-neural-sparql-machine-c35945a5d278)

## Contact

### Questions?
* Primary contacts: [Tommaso Soru](http://tommaso-soru.it) and [Edgard Marx](http://emarx.org).
* Neural SPARQL Machines [mailing list](https://groups.google.com/forum/#!forum/neural-sparql-machines).
* Join the conversation on [Gitter](https://gitter.im/LiberAI/community).

### Follow us
* Follow the [project on ResearchGate](https://www.researchgate.net/project/Neural-SPARQL-Machines).
* Follow Liber AI Research on [Twitter](https://twitter.com/theLiberAI).

NSpM

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

NSpM

File Explorer

Today's picks

Was this content helpful?

Recent Feedback

Download README