Skip to main content

A framework for evaluation and development of temporal-aware models.

Project description

tieval

PyPI Documentation Status PyPI - Python Version PyPI - License GitHub repo size

Paper

A framework for evaluation and development of temporally aware models.

Installation

The package is available on PyPI:

pip install tieval

It requires Python 3.8 or above.

Usage

To understand its usability refer to the notebooks available here.

Data

Throughout the last two decades many datasets have been developed to train this task. tieval provides an easy interface to download the available corpus.

To know more about the module run the following code on the terminal.

python -m tieval download --help

How to ...

In this section, we summarize how to perform the most useful operations in tieval.

download a dataset.

from pathlib import Path
from tieval import datasets

data_path = Path("data/")
datasets.download("TimeBank", data_path)

load a dataset.

from tieval import datasets

te3 = datasets.read("tempeval_3")

load a model.

from tieval import models

model = models.TimexIdentificationBaseline()

make predictions.

pred = model.predict(te3.test)

evaluate predictions.

from tieval import evaluate

annot = {doc.name: doc.timexs for doc in te3.test}
results = evaluate.timex_identification(annot, pred)

Contributing

  1. Fork it (https://github.com/LIAAD/tieval)
  2. Create your feature branch (git checkout -b feature/fooBar)
  3. Commit your changes (git commit -am 'Add some fooBar')
  4. Push to the branch (git push origin feature/fooBar)
  5. Create a new Pull Request

Meta

Hugo Sousa - hugo.o.sousa@inesctec.pt

This framework is part of the Text2Story project which is financed by the ERDF – European Regional Development Fund through the North Portugal Regional Operational Programme (NORTE 2020), under the PORTUGAL 2020 and by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia within project PTDC/CCI-COM/31857/2017 (NORTE-01-0145-FEDER-03185)

Publications

If you use tieval in your work please site the following article:

@inproceedings{10.1145/3539618.3591892,
    author = {Sousa, Hugo and Campos, Ricardo and Jorge, Al\'{\i}pio M\'{a}rio},
    title = {Tieval: An Evaluation Framework for Temporal Information Extraction Systems},
    year = {2023},
    isbn = {9781450394086},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3539618.3591892},
    doi = {10.1145/3539618.3591892},
    booktitle = {Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
    pages = {2871–2879},
    numpages = {9},
    keywords = {temporal information extraction, evaluation, python package},
    location = {Taipei, Taiwan},
    series = {SIGIR '23}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tieval-0.1.2.tar.gz (167.8 kB view details)

Uploaded Source

Built Distribution

tieval-0.1.2-py3-none-any.whl (36.3 kB view details)

Uploaded Python 3

File details

Details for the file tieval-0.1.2.tar.gz.

File metadata

  • Download URL: tieval-0.1.2.tar.gz
  • Upload date:
  • Size: 167.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.18

File hashes

Hashes for tieval-0.1.2.tar.gz
Algorithm Hash digest
SHA256 ff995f700b58552386127f8c832bedc1b680f4e43642aaea9283128a9ebf253e
MD5 e2dfcdc6c59f8969f00e37033a99a297
BLAKE2b-256 e34b09091274d5c7e29ac69c29abad90e21e395098ac7134da351825f9f7d81b

See more details on using hashes here.

File details

Details for the file tieval-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: tieval-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 36.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.18

File hashes

Hashes for tieval-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 ad2332e86f140ff6e292387f68be8dd21b07c146572a42f14168dbc85edf4dd8
MD5 d14efd608edb6c935dd8061984701722
BLAKE2b-256 59bc0dbf47cf581c324c0f6f5c40501e25315cc6b93f1180f0255a95412ba47e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page