metadata

license: cc-by-4.0
metrics:
  - bleu4
  - meteor
  - rouge-l
  - bertscore
  - moverscore
language: en
datasets:
  - lmqg/qg_squad
pipeline_tag: text2text-generation
tags:
  - question answering
widget:
  - text: >-
      question: What is a person called is practicing heresy?, context: Heresy
      is any provocative belief or theory that is strongly at variance with
      established beliefs or customs. A heretic is a proponent of such claims or
      beliefs. Heresy is distinct from both apostasy, which is the explicit
      renunciation of one's religion, principles or cause, and blasphemy, which
      is an impious utterance or action concerning God or sacred things.
    example_title: Question Answering Example 1
  - text: >-
      question: who created the post as we know it today?, context: 'So much of
      The Post is Ben,' Mrs. Graham said in 1994, three years after Bradlee
      retired as editor. 'He created it as we know it today.'— Ed O'Keefe
      (@edatpost) October 21, 2014
    example_title: Question Answering Example 2
model-index:
  - name: vocabtrimmer/mt5-small-trimmed-en-15000-squad-qa
    results:
      - task:
          name: Text2text Generation
          type: text2text-generation
        dataset:
          name: lmqg/qg_squad
          type: default
          args: default
        metrics:
          - name: BLEU4 (Question Answering)
            type: bleu4_question_answering
            value: 42.95
          - name: ROUGE-L (Question Answering)
            type: rouge_l_question_answering
            value: 71.59
          - name: METEOR (Question Answering)
            type: meteor_question_answering
            value: 42.33
          - name: BERTScore (Question Answering)
            type: bertscore_question_answering
            value: 92.23
          - name: MoverScore (Question Answering)
            type: moverscore_question_answering
            value: 82.99
          - name: AnswerF1Score (Question Answering)
            type: answer_f1_score__question_answering
            value: 73.42
          - name: AnswerExactMatch (Question Answering)
            type: answer_exact_match_question_answering
            value: 60.69

Model Card of `vocabtrimmer/mt5-small-trimmed-en-15000-squad-qa`

This model is fine-tuned version of ckpts/mt5-small-trimmed-en-15000 for question answering task on the lmqg/qg_squad (dataset_name: default) via lmqg.

Overview

Language model: ckpts/mt5-small-trimmed-en-15000
Language: en
Training data: lmqg/qg_squad (default)
Online Demo: https://autoqg.net/
Repository: https://github.com/asahi417/lm-question-generation
Paper: https://arxiv.org/abs/2210.03992

Usage

With lmqg

from lmqg import TransformersQG

# initialize model
model = TransformersQG(language="en", model="vocabtrimmer/mt5-small-trimmed-en-15000-squad-qa")

# model prediction
answers = model.answer_q(list_question="What is a person called is practicing heresy?", list_context=" Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.")

With transformers

from transformers import pipeline

pipe = pipeline("text2text-generation", "vocabtrimmer/mt5-small-trimmed-en-15000-squad-qa")
output = pipe("question: What is a person called is practicing heresy?, context: Heresy is any provocative belief or theory that is strongly at variance with established beliefs or customs. A heretic is a proponent of such claims or beliefs. Heresy is distinct from both apostasy, which is the explicit renunciation of one's religion, principles or cause, and blasphemy, which is an impious utterance or action concerning God or sacred things.")

Evaluation

Metric (Question Answering): raw metric file

	Score	Type	Dataset
AnswerExactMatch	60.69	default	lmqg/qg_squad
AnswerF1Score	73.42	default	lmqg/qg_squad
BERTScore	92.23	default	lmqg/qg_squad
Bleu_1	57.96	default	lmqg/qg_squad
Bleu_2	52.51	default	lmqg/qg_squad
Bleu_3	47.37	default	lmqg/qg_squad
Bleu_4	42.95	default	lmqg/qg_squad
METEOR	42.33	default	lmqg/qg_squad
MoverScore	82.99	default	lmqg/qg_squad
ROUGE_L	71.59	default	lmqg/qg_squad

Training hyperparameters

The following hyperparameters were used during fine-tuning:

dataset_path: lmqg/qg_squad
dataset_name: default
input_types: ['paragraph_question']
output_types: ['answer']
prefix_types: None
model: ckpts/mt5-small-trimmed-en-15000
max_length: 512
max_length_output: 32
epoch: 12
batch: 32
lr: 0.001
fp16: False
random_seed: 1
gradient_accumulation_steps: 2
label_smoothing: 0.15

The full configuration can be found at fine-tuning config file.

Citation

@inproceedings{ushio-etal-2022-generative,
    title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
    author = "Ushio, Asahi  and
        Alva-Manchego, Fernando  and
        Camacho-Collados, Jose",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, U.A.E.",
    publisher = "Association for Computational Linguistics",
}