Hugging Face's logo

Spaces:
Ikala-allen
/
relation_extraction
Runtime error

App Files Community
relation_extraction / README.md
Ikala-allen's picture
Ikala-allen
Update README.md
01078a4
preview code
|
raw
history blame
10.1 kB
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
license: apache-2.0

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 3 inputs, prediction, references(ground truth) and mode.Predictions and references are a list of list of dictionary of entity's name and entity's type. And mode define the evaluation type:

import evaluate
metric_path = "Ikala-allen/relation_extraction"
module = evaluate.load(metric_path)
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"},
  ]
]
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"},
  ]
]
evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict")

Inputs

  • predictions (list of list of dictionary): a list of list of dictionary with every element's relation_type and their entity name
  • references (list of list of dictionary): a list of list of dictionary with every element's relation_type and their entity name
  • mode (str): define strict or boundaries mode for evaluation, strict mode consider "head_type" and "tail_type", boundaries mode doesn't consider "head_type" and "tail_type"
  • only_all (bool): True for only output ["ALL"] relation_type score. False for output every relation_type score, default True
  • relation_types (list): define which relation type that need to be evaluate and show, if not given, it will construct relation_types from ground truth, default []

Output Values

output (dictionary of dictionarys) with multiple key-value pairs

  • ALL (dictionary): score of all of the relation type
    • 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
  • {selected relation type} (dictionary): score of selected relation type
    • tp : true positive count
    • fp : false positive count
    • fn : false negative count
    • p : precision
    • r : recall
    • f1 : micro f1 score

Output Example:

{'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}

Remind : 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

Example1 : only one prediction and reference, mode = strict, only output ALL relation score

metric_path = "Ikala-allen/relation_extraction"
module = evaluate.load(metric_path)
references = [
  [
    {"head": "phipigments", "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': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
  ]
]
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"},
  ]
]
evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict", only_all=True,relation_types = [])
print(evaluation_scores)
>>> {'tp': 1, 'fp': 1, 'fn': 2, 'p': 50.0, 'r': 33.333333333333336, 'f1': 40.0, 'Macro_f1': 25.0, 'Macro_p': 25.0, 'Macro_r': 25.0}

Example2 : only one prediction and reference, mode = boundaries, only output ALL relation score

metric_path = "Ikala-allen/relation_extraction"
module = evaluate.load(metric_path)
references = [
  [
    {"head": "phipigments", "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': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
  ]
]
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"},
  ]
]
evaluation_scores = module.compute(predictions=predictions, references=references, mode = "strict", only_all=True,relation_types = [])
print(evaluation_scores)
>>> {'tp': 2, 'fp': 0, 'fn': 1, 'p': 100.0, 'r': 66.66666666666667, 'f1': 80.0, 'Macro_f1': 50.0, 'Macro_p': 50.0, 'Macro_r': 50.0}

Example3 : two or more prediction and reference, mode = boundaries, only output = False, output all relation type score

metric_path = "Ikala-allen/relation_extraction"
module = evaluate.load(metric_path)
references = [
  [
    {"head": "phipigments", "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': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
  ]
]
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'}  
  ]
]
evaluation_scores = module.compute(predictions=predictions, references=references, mode = "boundaries", only_all = False, relation_types = [])
print(evaluation_scores)
>>> {'sell': {'tp': 3, 'fp': 1, 'fn': 0, 'p': 75.0, 'r': 100.0, 'f1': 85.71428571428571}, 'belongs_to': {'tp': 0, 'fp': 0, 'fn': 1, 'p': 0, 'r': 0, 'f1': 0}, 'ALL': {'tp': 3, 'fp': 1, 'fn': 1, 'p': 75.0, 'r': 75.0, 'f1': 75.0, 'Macro_f1': 42.857142857142854, 'Macro_p': 37.5, 'Macro_r': 50.0}}

Example 4 : two or more prediction and reference, mode = boundaries, only output = False, only output ALL relation score, relation_types = ["belongs_to"], only consider belongs_to type score

metric_path = "Ikala-allen/relation_extraction"
module = evaluate.load(metric_path)
references = [
  [
    {"head": "phipigments", "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': 'A醛賦活緊緻精華', 'tail': 'Serum', 'head_type': 'product', 'tail_type': 'category', 'type': 'belongs_to'},
  ]
]
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'}  
  ]
]
evaluation_scores = module.compute(predictions=predictions, references=references, mode = "boundaries", only_all=False,relation_types  = ["belongs_to"])
print(evaluation_scores)  
>>> {'belongs_to': {'tp': 0, 'fp': 0, 'fn': 1, 'p': 0, 'r': 0, 'f1': 0}, 'ALL': {'tp': 0, 'fp': 0, 'fn': 1, 'p': 0, 'r': 0, 'f1': 0, 'Macro_f1': 0.0, 'Macro_p': 0.0, 'Macro_r': 0.0}}

Limitations and Bias

This metric has strict and boundaries mode, also can select relation_types for different type evaluation. Make sure to select suitable evaluation parameters. F1 score may be totally different. Prediction and reference entity_name should be exactly the same regardless of case and spaces. If prediction is not exactly the same as the reference one. It will count as fp or fn.

Citation 

@Paper{
    author = {Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten, Patrick Gallinari},
    title = {Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!},
    year = {2020},
    link = https://arxiv.org/abs/2009.10684
}

Further References

This evaluation metric implementation uses https://github.com/btaille/sincere/blob/master/code/utils/evaluation.py