https://github.com/ggordonhall/measurement_tagger

Spacy Measurement Tagger
https://github.com/ggordonhall/measurement_tagger

dependency-parser measurement-tagger nlp python spacy tagger

Last synced: 18 days ago
JSON representation

Spacy Measurement Tagger

• Host: GitHub
• URL: https://github.com/ggordonhall/measurement_tagger
• Owner: ggordonhall
• Created: 2018-10-12T13:01:13.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-12-13T15:40:16.000Z (about 6 years ago)
• Last Synced: 2024-11-07T01:39:04.530Z (2 months ago)
• Topics: dependency-parser, measurement-tagger, nlp, python, spacy, tagger
• Language: Python
• Homepage:
• Size: 84 KB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Measurement Tagger

[![Build Status](https://travis-ci.org/ggordonhall/measurement_tagger.png)](https://travis-ci.org/ggordonhall/measurement_tagger)

[![codecov](https://codecov.io/gh/ggordonhall/measurement_tagger/branch/master/graph/badge.svg)](https://codecov.io/gh/ggordonhall/measurement_tagger)

## A dependency parse based measurement tagger.

Text to be tagged should be stored in the `text/` directory. The file to tag is specific with `-t`.

Run in mode (`-m`):

| Mode    | Measurement   |

| --------|:-------------:|

| `d`     | Distance      |

| `t`     | Time          |

| `m`     | Mass          |

| `e`     | Energy        |

| `v`     | Volume        |

By default, tags measurements then convertes them to their standard unit. Unconverted measurements can be returned if run with the `--return_unconverted` flag. The maximum n-gram to search for measurement units, i.e. `nautical miles`, can be set with the 

`--max_gram` flag.

Run `pipenv install && python -m spacy download en && python -m nltk.downloader wordnet` to setup, then test by running `main.py -m d -t wiki.txt`.

## TO DO

- [ ] Fix `--parallel` flag

- [x] Improve handling of n-gram measurement units