十年网站开发经验 + 多家企业客户 + 靠谱的建站团队
量身定制 + 运营维护+专业推广+无忧售后,网站问题一站解决
要求:
为通辽等地区用户提供了全套网页设计制作服务,及通辽网站建设行业解决方案。主营业务为做网站、成都网站建设、通辽网站设计,以传统方式定制建设网站,并提供域名空间备案等一条龙服务,秉承以专业、用心的态度为用户提供真诚的服务。我们深信只要达到每一位用户的要求,就会得到认可,从而选择与我们长期合作。这样,我们也可以走得更远!1 采用基于语言模型的大概率法进行汉语切分。
2 切分算法中的语言模型可以采用n-gram语言模型,要求n >1,并至少采用一种平滑方法;
代码:
废话不说,代码是最好的语言
import re import math MAX_SPLITLEN = 4#大切分长度 corpus_lib = ''#corpus:语料 def init_corpus_lib(path): # 初始化语料库 global corpus_lib with open(path, 'r', encoding='utf-8', errors='ignore') as file: corpus_lib = str(file.readlines()) def get_candidate_words(sen): global MAX_SPLITLEN global corpus_lib candidate_words = [] for sp in range(len(sen)): w = sen[sp] candidate_words.append([w, sp, sp]) # 有些字可能不在语料库中,把它作为单个字加进去 for mp in range(1, MAX_SPLITLEN): # 判断1 ~ MAX_SPLITLEN-1这3种词中是否有候选词. if sp + mp < len(sen): w += sen[sp + mp] if w in corpus_lib: candidate_words.append([w, sp, sp + mp]) # 存储词,初始位置,结束位置 print('候选词有:%s' % candidate_words) return candidate_words def segment_sentence(sen): # sen:sentence即要切分的句子 global MAX_SPLITLEN global corpus_lib candidate_words = get_candidate_words(sen) count = 0 for word in candidate_words: if count > 1000: # 为防止对长句子解析时间过长,放弃一部分精度追求效率 break if word[1] == 0 and word[2] != len(sen) - 1: # 如果句子中开头的部分,还没有拼凑成整个词序列的话 no_whitespace_sen = ''.join(word[0].split()) for word in candidate_words: # word比如:['今天', 1, 2],1是今在句子中的位置,2是天的位置 if word[1] == 0 and word[2] != len(sen) - 1: end = word[2] for later_word in candidate_words: if later_word[1] == end + 1: # 如果later_word是当前词的后续词,那么拼接到当前词上 word_seq = [word[0] + ' ' + later_word[0], word[1], later_word[2]] # 合并 candidate_words.append(word_seq) # print('拼出了新词:%s' % word_seq) count += 1 candidate_words.remove(word) # 遍历完后,这个开头部分短语要移除掉,不然下次遍历还会对它做无用功 print('所有结果词序列有:%s' % candidate_words) word_segment_res_list = [] # 存储分词结果序列 for seque in candidate_words: if seque[1] == 0 and seque[2] == len(sen) - 1: word_segment_res_list.append(seque[0]) print('获得的所有分词结果是:') print(word_segment_res_list) return word_segment_res_list # P(w1,w2,...,wn) = P(w1/start)P(w2/w1)P(w3/w2).....P(Wn/Wn-1) # 下标从0开始: = P(w0/start)P(w1/w0)...P(Wn-1/Wn-2) def calculate_word_sequence_probability(sequence): global corpus_lib word_list = sequence.split(' ') total_word_num = len(corpus_lib) prob_total = 0.0 word_start = word_list[0] # 计算第一个词出现的概率P(w1/start)=Count(w1)/total count = len(re.findall(r'\s' + word_start + r'\s', corpus_lib)) + 1 # 加1平滑 prob_total += math.log(count / total_word_num) # 计算P(w2/w1)P(w3/w2).....P(Wn/Wn-1) for i in range(len(word_list) - 1): # 0~ n-2 prev_w = word_list[i] later_w = word_list[i + 1] count = len(re.findall(r'\s' + prev_w + r'\s' + later_w + r'\s', corpus_lib)) count += 1 # 做一次加1平滑 prob_total += math.log(count / total_word_num) print('%s的概率是:' % sequence) print(prob_total) return prob_total def calculate_biggest_prob(word_segm_res): best_w_s = '' max_prob = 0.0 for w_s in word_segm_res: # 改进:先只计算词的数目<=0.6 句子字数的,如果不行再计算全部的概率 no_whitespace_sen = ''.join(w_s.split()) zi_shu = len(no_whitespace_sen) if len(w_s.split(' ')) <= zi_shu * 0.6: prob = calculate_word_sequence_probability(w_s) if max_prob == 0 or max_prob < prob: best_w_s = w_s max_prob = prob if best_w_s == '': # 如果上面的0.6不行的话,再计算全部的概率 prob = calculate_word_sequence_probability(w_s) if max_prob == 0 or max_prob < prob: best_w_s = w_s max_prob = prob print('最好的分词结果(概率为%s)是 :%s' % (math.pow(math.e, max_prob), best_w_s)) return best_w_s def split_middle(sen_to_segment): # 从中间切分一下,返回中间切分的位置 length = len(sen_to_segment) start = int(length / 2) - 2 end = start + 5 # 对中间的5个字进行切分,然后找第一个空格,按此把整个句子一分为二 middle_part = sen_to_segment[start:end] best_segm_res = calculate_biggest_prob(segment_sentence(middle_part)) return start + best_segm_res.index(' ') - 1 def split_mark_and_too_long_sent(sentences): # 按任意标点符号划分句子,对每个短句进行分词 sen_list = sentences.splitlines() print(sen_list) out_text = '' for line in sen_list: sen_to_segment = '' # for single_char in line: if single_char.isalpha(): # isalpha()表示是否是单词,如果是单词的为True,标点符号等为False sen_to_segment += single_char elif not single_char.isalpha() and sen_to_segment == '': # 如果single_char是标点符号、数字,且前面没有待分词的句子 out_text += single_char + ' ' print(single_char) else: # 如果single_char是标点符号、数字, # 如果句子太长,先从中间切分一下 if len(sen_to_segment) >= 20: middle = split_middle(sen_to_segment) left_half = sen_to_segment[0:middle + 1] # 左半部分 best_segm_res = calculate_biggest_prob(segment_sentence(left_half)) out_text += best_segm_res + ' ' sen_to_segment = sen_to_segment[middle + 1:len(sen_to_segment)] # 右半部分交给后面几行处理 best_segm_res = calculate_biggest_prob(segment_sentence(sen_to_segment)) print(single_char) sen_to_segment = '' out_text += best_segm_res + ' ' + single_char + ' ' # 标点两侧也用空格隔起来 # 如果这行句子最后还有一些文字没有切分的话 if sen_to_segment != '': best_segm_res = calculate_biggest_prob(segment_sentence(sen_to_segment)) out_text += best_segm_res + ' ' out_text += '\n' with open('D:/1佩王的文件/计算语言学基础/生成结果.txt','w') as file: file.write(out_text) print(out_text) if __name__ == '__main__': path = 'D:/1佩王的文件/计算语言学基础/北大(人民日报)语料库199801.txt' init_corpus_lib(path)#初始化语料库 sentences = '' path = 'E:/study/1.研一的课/计算语言学基础课件/testset.txt'#读取要切分的文章 with open(path, 'r', encoding='gbk', errors='ignore') as file: for line in file.readlines(): sentences += line # 改进:先对句子按标点符号划分成多个短句,然后对每个短句进行切分、计算概率 split_mark_and_too_long_sent(sentences)