多语言XLM-RoBERTa大型机器阅读理解模型

概述

语言模型：xlm-roberta-large 语言：多语言下游任务：提取式问答训练数据：SQuAD 2.0 评估数据：SQuAD开发集 - 德语MLQA - 德语XQuAD 训练次数： MLFlow link 基础设施：4x Tesla v100

超参数

batch_size = 32
n_epochs = 3
base_LM_model = "xlm-roberta-large"
max_seq_len = 256
learning_rate = 1e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

性能

在SQuAD 2.0英语开发集上进行评估，得分为 official eval script

  "exact": 79.45759285774446,
  "f1": 83.79259828925511,
  "total": 11873,
  "HasAns_exact": 71.96356275303644,
  "HasAns_f1": 80.6460053117963,
  "HasAns_total": 5928,
  "NoAns_exact": 86.93019343986543,
  "NoAns_f1": 86.93019343986543,
  "NoAns_total": 5945

在德语上评估得分为 MLQA: test-context-de-question-de.json

"exact": 49.34691166703564,
"f1": 66.15582561674236,
"total": 4517,

在德语上评估得分为 XQuAD: xquad.de.json

"exact": 61.51260504201681,
"f1": 78.80206098332569,
"total": 1190,

使用方法

在Haystack中

要进行大规模问答（即多个文档而不是单个段落），您也可以在 haystack 中加载该模型：

reader = FARMReader(model_name_or_path="deepset/xlm-roberta-large-squad2")
# or 
reader = TransformersReader(model="deepset/xlm-roberta-large-squad2",tokenizer="deepset/xlm-roberta-large-squad2")

在Transformers中

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/xlm-roberta-large-squad2"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)