用微调的BERT回答问题

!pip install transformers

import pandas as pd
import numpy as np
import torch
from transformers import BertForQuestionAnswering
from transformers import BertTokenizer

coqa = pd.read_json('http://downloads.cs.stanford.edu/nlp/data/coqa/coqa-train-v1.0.json')
coqa.head()

del coqa["version"]

# 数据框中的必需列
cols = ["text","question","answer"]

# 创建数据帧的列表的列表
comp_list = []
for index, row in coqa.iterrows():
    for i in range(len(row["data"]["questions"])):
        temp_list = []
        temp_list.append(row["data"]["story"])
        temp_list.append(row["data"]["questions"][i]["input_text"])
        temp_list.append(row["data"]["answers"][i]["input_text"])
        comp_list.append(temp_list)

new_df = pd.DataFrame(comp_list, columns=cols) 

# 将数据帧保存到csv文件以供进一步加载
new_df.to_csv("CoQA_data.csv", index=False)

data = pd.read_csv("CoQA_data.csv")
data.head()

print("Number of question and answers: ", len(data))

Number of question and answers:  108647

model = BertForQuestionAnswering.from_pretrained('bert-large-uncased-whole-word-masking-finetuned-squad')
tokenizer = BertTokenizer.from_pretrained('bert-large-uncased-whole-word-masking-finetuned-squad')

random_num = np.random.randint(0,len(data))

question = data["question"][random_num]
text = data["text"][random_num]

input_ids = tokenizer.encode(question, text)
print("The input has a total of {} tokens.".format(len(input_ids)))

The input has a total of 427 tokens.

tokens = tokenizer.convert_ids_to_tokens(input_ids)

for token, id in zip(tokens, input_ids):
    print('{:8}{:8,}'.format(token,id))

# 首次出现[SEP]token
sep_idx = input_ids.index(tokenizer.sep_token_id)
print("SEP token index: ", sep_idx)

#段A中的token数 (question) - 这将比sep_idx多一个，因为Python中的索引从0开始
num_seg_a = sep_idx+1
print("Number of tokens in segment A: ", num_seg_a)

# 段B中的token数（文本）
num_seg_b = len(input_ids) - num_seg_a
print("Number of tokens in segment B: ", num_seg_b)

# 创建段ID
segment_ids = [0]*num_seg_a + [1]*num_seg_b

# 确保每个输入token都有一个段id
assert len(segment_ids) == len(input_ids)

SEP token index: 8
Number of tokens in segment A: 9
Number of tokens in segment B: 418

#token input_ids to 表示输入，token segment_id用于区分我们的段
output = model(torch.tensor([input_ids]),  token_type_ids=torch.tensor([segment_ids]))

# 开始和结束分数最高的token
answer_start = torch.argmax(output.start_logits)
answer_end = torch.argmax(output.end_logits)

if answer_end >= answer_start:
    answer = " ".join(tokens[answer_start:answer_end+1])
else:
    print("I am unable to find the answer to this question. Can you please ask another question?")

print("\nQuestion:\n{}".format(question.capitalize()))
print("\nAnswer:\n{}.".format(answer.capitalize()))

Question:
Who is the acas director?

Answer:
Agnes karin ##gu.

answer = tokens[answer_start]

for i in range(answer_start+1, answer_end+1):
    if tokens[i][0:2] == "##":
        answer += tokens[i][2:]
    else:
        answer += " " + tokens[i]

def question_answer(question, text):

    # 将问题和文本token化
    input_ids = tokenizer.encode(question, text)

    #字符串版本
    tokens = tokenizer.convert_ids_to_tokens(input_ids)

    #段IDs
    #first occurence of [SEP] token
    sep_idx = input_ids.index(tokenizer.sep_token_id)

    # 段A中的token数
    num_seg_a = sep_idx+1

    # 段B中的token数
    num_seg_b = len(input_ids) - num_seg_a

    # 段嵌入的0和1列表
    segment_ids = [0]*num_seg_a + [1]*num_seg_b
    assert len(segment_ids) == len(input_ids)

    # 使用input_ids和segment_ids的模型输出
    output = model(torch.tensor([input_ids]), token_type_ids=torch.tensor([segment_ids]))

    # 重建答案
    answer_start = torch.argmax(output.start_logits)
    answer_end = torch.argmax(output.end_logits)

    if answer_end >= answer_start:
        answer = tokens[answer_start]
        for i in range(answer_start+1, answer_end+1):
            if tokens[i][0:2] == "##":
                answer += tokens[i][2:]
            else:
                answer += " " + tokens[i]

    if answer.startswith("[CLS]"):
        answer = "Unable to find the answer to your question."

    print("\nPredicted answer:\n{}".format(answer.capitalize()))

text = """New York (CNN) -- More than 80 Michael Jackson collectibles -- including the late pop star's famous rhinestone-studded glove from a 1983 performance -- were auctioned off Saturday, reaping a total $2 million. Profits from the auction at the Hard Rock Cafe in New York's Times Square crushed pre-sale expectations of only $120,000 in sales. The highly prized memorabilia, which included items spanning the many stages of Jackson's career, came from more than 30 fans, associates and family members, who contacted Julien's Auctions to sell their gifts and mementos of the singer. Jackson's flashy glove was the big-ticket item of the night, fetching $420,000 from a buyer in Hong Kong, China. Jackson wore the glove at a 1983 performance during \"Motown 25,\" an NBC special where he debuted his revolutionary moonwalk. Fellow Motown star Walter \"Clyde\" Orange of the Commodores, who also performed in the special 26 years ago, said he asked for Jackson's autograph at the time, but Jackson gave him the glove instead. "The legacy that [Jackson] left behind is bigger than life for me,\" Orange said. \"I hope that through that glove people can see what he was trying to say in his music and what he said in his music.\" Orange said he plans to give a portion of the proceeds to charity. Hoffman Ma, who bought the glove on behalf of Ponte 16 Resort in Macau, paid a 25 percent buyer's premium, which was tacked onto all final sales over $50,000. Winners of items less than $50,000 paid a 20 percent premium."""

question = "Where was the Auction held?"

question_answer(question, text)

#数据集的原始答案
print("Original answer:\n", data.loc[data["question"] == question]["answer"].values[0]))

Predicted answer:
Hard rock cafe in new york ' s times square

Original answer:
Hard Rock Cafe

text = input("Please enter your text: \n")
question = input("\nPlease enter your question: \n")

while True:
    question_answer(question, text)

    flag = True
    flag_N = False

    while flag:
        response = input("\nDo you want to ask another question based on this text (Y/N)? ")
        if response[0] == "Y":
            question = input("\nPlease enter your question: \n")
            flag = False
        elif response[0] == "N":
            print("\nBye!")
            flag = False
            flag_N = True

    if flag_N == True:
        break

Please enter your text: 
The Vatican Apostolic Library (), more commonly called the Vatican Library or simply the Vat, is the library of the Holy See, located in Vatican City. Formally established in 1475, although it is much older, it is one of the oldest libraries in the world and contains one of the most significant collections of historical texts. It has 75,000 codices from throughout history, as well as 1.1 million printed books, which include some 8,500 incunabula.   The Vatican Library is a research library for history, law, philosophy, science and theology. The Vatican Library is open to anyone who can document their qualifications and research needs. Photocopies for private study of pages from books published between 1801 and 1990 can be requested in person or by mail.   In March 2014, the Vatican Library began an initial four-year project of digitising its collection of manuscripts, to be made available online.   The Vatican Secret Archives were separated from the library at the beginning of the 17th century; they contain another 150,000 items.   Scholars have traditionally divided the history of the library into five periods, Pre-Lateran, Lateran, Avignon, Pre-Vatican and Vatican.   The Pre-Lateran period, comprising the initial days of the library, dated from the earliest days of the Church. Only a handful of volumes survive from this period, though some are very significant.

Please enter your question: 
When was the Vat formally opened?

Answer:
1475

Do you want to ask another question based on this text (Y/N)? Y

Please enter your question: 
what is the library for?

Answer:
Research library for history , law , philosophy , science and theology

Do you want to ask another question based on this text (Y/N)? Y

Please enter your question: 
for what subjects?

Answer:
History , law , philosophy , science and theology
Do you want to ask another question based on this text (Y/N)? N

Bye!