Project description

paraphrase-metrics

Metrics for better understanding of Paraphrases

pip install paraphrase-metrics

About

A python package containing implementations of word position deviation (WPD) and lexical deviation (LD) proposed in "Towards Better Characterization of Paraphrases" (ACL 2022).

For a simple demo, please see demo.ipynb.

Paper

The full code associated with the ACL 2022 paper "Towards Better Characterization of Paraphrases" can be found in the ./paper/ folder.

Project details

These details have not been verified by PyPI

Project links

GitHub Statistics

Release history Release notifications | RSS feed

This version

0.0.1

Mar 9, 2022

Download files

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

Source Distribution

paraphrase-metrics-0.0.1.tar.gz (3.9 kB view hashes)

Uploaded Mar 9, 2022 Source

Built Distribution

paraphrase_metrics-0.0.1-py3-none-any.whl (4.3 kB view hashes)

Uploaded Mar 9, 2022 Python 3

Hashes for paraphrase-metrics-0.0.1.tar.gz

Hashes for paraphrase-metrics-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`31891135c04f4687e6efb8a24432181121b86ef26da660b5040a68bc09a444b8`
MD5	`b32486d17bea6c581e5c89c623ebc054`
BLAKE2b-256	`cb830d5d2322266d7f02e98e64d7e9ab3f100afba1a95584f9f4bdf2642bdc5b`

Hashes for paraphrase_metrics-0.0.1-py3-none-any.whl

Hashes for paraphrase_metrics-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`5d53214fc3cea8b8b993fb8df3578c17b5d0f187455852dfcbf19673b7fdf1a7`
MD5	`933804e6f1c000443004a3818535884c`
BLAKE2b-256	`b24fa8865b656079c0548e9fa290202e1d9cbc999deac3787135a0b691e0b363`