README.md

metadata

title: relation_extraction
datasets:
  - none
tags:
  - evaluate
  - metric
description: >-
  This metric is used for evaluating the F1 accuracy of input references and
  predictions.
sdk: gradio
sdk_version: 3.19.1
app_file: app.py
pinned: false

Metric Card for relation_extraction evalutation

This metric is used for evaluating the quality of relation extraction output. By calculating the Micro and Macro F1 score of every relation extraction outputs to ensure the quality.

Metric Description

This metric can be used in relation extraction evaluation.

How to Use

This metric takes 2 inputs, prediction and references(ground truth). Both of them are a list of list of dictionary of entity's name and entity's type:

import evaluate

#### load metric
>>> metric_path = "Ikala-allen/relation_extraction"
>>> module = evaluate.load(metric_path)

#### Define your predictions and references
#### Example references (ground truth)
>>> references = [
...    [
...       {"head": "phip igments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...    ]
... ]

#### Example predictions
>>> predictions = [
...    [
...        {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...    ]
... ]

#### Calculate evaluation scores using the loaded metric
>>> evaluation_scores = module.compute(predictions=predictions, references=references)
>>> print(evaluation_scores)
{'sell': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0}, 'ALL': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}}

Inputs

• predictions (list of lists of dictionarys): relation and its type of prediction
• references (list of lists of dictionarys): references for each relation and its type.

Output Values

output (dictionary of dictionarys) with multiple key-value pairs - sell (dictionary): score of type sell - tp : true positive count - fp : false positive count - fn : false negative count - p : precision - r : recall - f1 : micro f1 score - ALL (dictionary): score of all of the type (sell and belongs to) - tp : true positive count - fp : false positive count - fn : false negative count - p : precision - r : recall - f1 : micro f1 score - Macro_f1 : macro f1 score - Macro_p : macro precision - Macro_r : macro recall

Output Example:

{'sell': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0}, 'ALL': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}}

Macro_f1、Macro_p、Macro_r、p、r、f1 are always a number between 0 and 1. And tp、fp、fn depend on how many data inputs.

Examples

Example of only one prediction and reference:

>>> metric_path = "Ikala-allen/relation_extraction"
>>> module = evaluate.load(metric_path)

#### Define your predictions and references
#### Example references (ground truth)
>>> references = [
...    [
...       {"head": "phip igments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...    ]
... ]

#### Example predictions
>>> predictions = [
...    [
...        {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...    ]
... ]

#### Calculate evaluation scores using the loaded metric
>>> evaluation_scores = module.compute(predictions=predictions, references=references)
>>> print(evaluation_scores)
{'sell': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0}, 'ALL': {'tp': 1, 'fp': 1, 'fn': 1, 'p': 50.0, 'r': 50.0, 'f1': 50.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}}

Example with two or more prediction and reference:

>>> metric_path = "Ikala-allen/relation_extraction"
>>> module = evaluate.load(metric_path)

#### Define your predictions and references
#### Example references (ground truth)
>>> references = [
...     [
...         {"head": "phip igments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...         {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...     ],[
...           {'head': 'SABONTAIWAN', 'tail': '大馬士革玫瑰有機光燦系列', 'head_type': 'brand', 'tail_type': 'product', 'type': 'sell'},
...           {'head': 'SABONTAIWAN', 'tail': '大馬士革玫瑰有機光燦系列', 'head_type': 'brand', 'tail_type': 'product', 'type': 'sell'}  
...     ]
...   ]

#### Example predictions
>>> predictions = [
...    [
...        {"head": "phipigments", "head_type": "product", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...        {"head": "tinadaviespigments", "head_type": "brand", "type": "sell", "tail": "國際認證之色乳", "tail_type": "product"},
...    ],[
...          {'head': 'SABONTAIWAN', 'tail': '大馬士革玫瑰有機光燦系列', 'head_type': 'brand', 'tail_type': 'product', 'type': 'sell'},
...          {'head': 'SNTAIWAN', 'tail': '大馬士革玫瑰有機光燦系列', 'head_type': 'brand', 'tail_type': 'product', 'type': 'sell'}  
...    ]
...  ]

#### Calculate evaluation scores using the loaded metric
>>> evaluation_scores = module.compute(predictions=predictions, references=references)
>>> print(evaluation_scores)
{'sell': {'tp': 2, 'fp': 2, 'fn': 1, 'p': 50.0, 'r': 66.66666666666667, 'f1': 57.142857142857146}, 'ALL': {'tp': 2, 'fp': 2, 'fn': 1, 'p': 50.0, 'r': 66.66666666666667, 'f1': 57.142857142857146, 'Macro_f1': 57.142857142857146, 'Macro_p': 50.0, 'Macro_r': 66.66666666666667}}

Limitations and Bias

This metric has multiple known limitations:

Citation

Cite the source where this metric was introduced.

Further References

Add any useful further references.