def locationNER(text): #先分词 segmentor = Segmentor() # 初始化实例 segmentor.load(cws_model_path) # 加载模型 words = segmentor.segment(text) # 分词 #print ('\t'.join(words)) segmentor.release() #再词性标注 postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 postags = postagger.postag(words) # 词性标注 postagger.release() # 释放模型 #最后地理实体识别 recognizer = NamedEntityRecognizer() # 初始化实例 recognizer.load(ner_model_path) # 加载模型 netags = recognizer.recognize(words, postags) # 命名实体识别 for i in range (0,len(netags)): if 'I-Ns'in netags[i] or 'I-Ni'in netags[i]: results.append(words[i-1]+words[i]+words[i+1]) if 'S-Ns'in netags[i] or 'S-Ni'in netags[i]: results.append(words[i]) return results
def word_pos(): #ltp词性标注 candidate=pd.read_csv(r'../data/candidate_sentiment.csv',header=None) can_word=candidate[0].tolist() # 新加一列存放词性 candidate.insert(2,'ltp_pos',0) candidate.insert(3,'jieba_pos',0) candidate.columns=['word','freq','ltp_pos','jieba_pos'] LTP_DATA_DIR = '../ltp_data_v3.4.0/ltp_data_v3.4.0' # ltp模型目录的路径 pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # 词性标注模型路径,模型名称为`pos.model` postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 postags = postagger.postag(can_word) # 词性标注 postagger.release() # 释放模型 postags=list(postags) candidate['ltp_pos']=postags #jieba词性标注 jieba_pos=[] for index,row in candidate.iterrows(): s=row['word'] words=pseg.cut(s) pos=[] for w in words: pos.append(w.flag) pos=' '.join(pos) jieba_pos.append(pos) candidate['jieba_pos']=jieba_pos # 添加表头 candidate.to_csv(r'../data/candidate_sentiment.csv',index=None)
def cut_words(): #分词+去除空行 #词性标注集http://ltp.readthedocs.io/zh_CN/latest/appendix.html cont = open('resource_new.txt', 'r', encoding='utf-8') f = open('key/cut_resouce.txt', 'w', encoding='utf-8') segmentor = Segmentor() # 初始化实例 # segmentor.load('cws.model') # 加载模型,不加载字典 segmentor.load_with_lexicon('module/cws.model', 'userdict.txt') # 加载模型,加载用户字典 postagger = Postagger() # 初始化实例 postagger.load('module/pos.model') # 加载模型 for sentence in cont: if sentence.strip() != '': words = segmentor.segment(sentence) # 分词 pos_tags = postagger.postag(words) # 词性标注 for word, tag in zip(words, pos_tags): if tag != 'wp': f.write(word) else: f.write('\n') f.write('\n') else: continue f.close() segmentor.release() postagger.release()
def segmentsentence(sentence): segmentor = Segmentor() postagger = Postagger() parser = Parser() recognizer = NamedEntityRecognizer() segmentor.load("./ltpdata/ltp_data_v3.4.0/cws.model") postagger.load("./ltpdata/ltp_data_v3.4.0/pos.model") # parser.load("./ltpdata/ltp_data_v3.4.0/parser.model") recognizer.load("./ltpdata/ltp_data_v3.4.0/ner.model") ############# word_list = segmentor.segment(sentence) postags_list = postagger.postag(word_list) nertags = recognizer.recognize(word_list, postags_list) ############ for word, ntag in zip(word_list, nertags): if ntag == 'Nh': entity_list.append(word) print(" ".join(word_list)) print(' '.join(nertags)) ############ segmentor.release() postagger.release() # parser.release() recognizer.release() return word_list
def get_postags(self, words): postagger = Postagger() # 初始化实例 postagger.load(self.pos_model_path) # 加载模型 postags = postagger.postag(words) # 词性标注 print('\t'.join(postags)) postagger.release() # 释放模型 return list(postags)
class LTP: def __init__(self): self.segmentor = Segmentor() # 分词器 self.segmentor.load_with_lexicon( Config.SEGMENTOR_PATH, Config.PERSONAL_SEGMENTOR_PATH) # 加载模型 self.postagger = Postagger() # 词性分析器 self.postagger.load(Config.POSTAGGER_PATH) # 加载模型 self.parser = Parser() # 句法分析器 self.recognizer = NamedEntityRecognizer() self.recognizer.load(Config.NAMED_ENTITY_RECONGNTION_PATH) self.parser.load(Config.PARSER_PATH) # 加载模型 self.labeller = SementicRoleLabeller() # 语义角色分析器 self.labeller.load(Config.LABELLER_PATH) # 加载模型 self.negative_list = get_negative_list() self.no_list = get_no_list() self.limit_list = get_limit_list() self.special_list = get_special_list() self.key_sentences = [] def __del__(self): """ 资源释放 """ self.segmentor.release() self.postagger.release() self.parser.release() self.labeller.release()
def get_postag_list(words_list): postag = Postagger() postag.load(pos_model_path) postag_list = list(postag.postag(words_list)) postag.release() return postag_list
class pyltp_model(): def __init__(self, LTP_DATA_DIR='/Users/didi/Desktop/ltp_data_v3.4.0'): cws_model_path = os.path.join(LTP_DATA_DIR, 'cws.model') pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') ner_model_path = os.path.join( LTP_DATA_DIR, 'ner.model') # 命名实体识别模型路径,模型名称为`pos.model` self.segmentor = Segmentor() # 初始化实例 self.postagger = Postagger() # 初始化实例 self.recognizer = NamedEntityRecognizer() # 初始化实例 self.segmentor.load(cws_model_path) # 加载模型 self.postagger.load(pos_model_path) # 加载模型 self.recognizer.load(ner_model_path) # 加载模型 def token(self, sentence): words = self.segmentor.segment(sentence) # 分词 words = list(words) postags = self.postagger.postag(words) # 词性标注 postags = list(postags) netags = self.recognizer.recognize(words, postags) # 命名实体识别 netags = list(netags) result = [] for i, j in zip(words, netags): if j in ['S-Nh', 'S-Ni', 'S-Ns']: result.append(j) continue result.append(i) return result def close(self): self.segmentor.release() self.postagger.release() self.recognizer.release() # 释放模型
def extract_views(all_sents): segmentor = Segmentor() segmentor.load(r'/home/student/project-01/ltp_data/cws.model') postagger = Postagger() postagger.load(r'/home/student/project-01/ltp_data/pos.model') parser = Parser() parser.load(r'/home/student/project-01/ltp_data/parser.model') views_in_sents = [] for i, sents in enumerate(all_sents): views_tmp = [] for sent in sents: sent = sent.replace('\\n', '\n').strip() if len(sent) == 0: continue # words = list(jieba.cut(sent)) words = list(segmentor.segment(sent)) contains = contain_candidates(words) if len(contains) == 0: continue tags = list(postagger.postag(words)) arcs = list(parser.parse(words, tags)) sbv, head = get_sbv_head(arcs, words, tags) if sbv[0] is None or head[0] is None or head[0] not in contains: continue subj = sbv[0] view = clean_view(words[head[1] + 1:]) views_tmp.append((subj, view, i)) if len(views_tmp) > 0: views_in_sents.append({'sents': sents, 'views': views_tmp}) segmentor.release() postagger.release() parser.release() return views_in_sents
def postags_opt(words): # Set pyltp postagger model path LTP_DATA_DIR = '../ltp_data_v3.4.0' pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # Init postagger postagger = Postagger() # Load model postagger.load(pos_model_path) # Get postags postags = postagger.postag(words) # Close postagger postagger.release() postags = list(postags) # Init result list saying_words = [] # Filter with tag 'verb' for index, tag in enumerate(postags): if tag == 'v': saying_words.append(words[index]) return saying_words
def ltp_word(self): """创建一个方法,用来进行句子的分词、词性分析等处理。""" # 分词 segmentor = Segmentor() segmentor.load(os.path.join(MODELDIR, "cws.model")) words = segmentor.segment(self.content) #print("*************分词*****************") #print("\t".join(words)) # 词性标注 postagger = Postagger() postagger.load(os.path.join(MODELDIR, "pos.model")) postags = postagger.postag(words) #print("*************词性标注*************") #print(type(postags)) #print("\t".join(postags)) # 依存句法分析 parser = Parser() parser.load(os.path.join(MODELDIR, "parser.model")) arcs = parser.parse(words, postags) #print("*************依存句法分析*************") #print(type(arcs)) #print("\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs)) # 把依存句法分析结果的head和relation分离出来 arcs_head = [] arcs_relation = [] for arc in arcs: arcs_head.append(arc.head) arcs_relation.append(arc.relation) # 命名实体识别 recognizer = NamedEntityRecognizer() recognizer.load(os.path.join(MODELDIR, "ner.model")) netags = recognizer.recognize(words, postags) #print("*************命名实体识别*************") #print("\t".join(netags)) """ # 语义角色标注 labeller = SementicRoleLabeller() labeller.load(os.path.join(MODELDIR, "pisrl.model")) roles = labeller.label(words, postags, arcs) print("*************语义角色标注*************") for role in roles: print(role.index, "".join( ["%s:(%d,%d)" % (arg.name, arg.range.start, arg.range.end) for arg in role.arguments])) """ segmentor.release() postagger.release() parser.release() recognizer.release() #labeller.release() # 调用list_conversion函数,把处理结果列表化 words_result = list_conversion(words, postags, netags, arcs_head, arcs_relation) return words_result
def get_postag_list(self, word_list, model): # 得到词性标注 postag = Postagger() postag.load(model) postag_list = list(postag.postag(word_list)) postag.release() return postag_list
class LtpLanguageAnalysis(object): def __init__(self, model_dir="/home/xxx/ltp-3.4.0/ltp_data/"): self.segmentor = Segmentor() self.segmentor.load(os.path.join(model_dir, "cws.model")) self.postagger = Postagger() self.postagger.load(os.path.join(model_dir, "pos.model")) self.parser = Parser() self.parser.load(os.path.join(model_dir, "parser.model")) def analyze(self, text): # 分词 words = self.segmentor.segment(text) print '\t'.join(words) # 词性标注 postags = self.postagger.postag(words) print '\t'.join(postags) # 句法分析 arcs = self.parser.parse(words, postags) print "\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs) def release_model(self): # 释放模型 self.segmentor.release() self.postagger.release() self.parser.release()
def ltp_pos_data(): """使用 LTP 进行词性标注""" LTP_DATA_DIR = 'D:\BaiduNetdiskDownload\ltp_data_v3.4.0' # ltp模型目录的路径 pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # 词性标注模型路径,模型名称为`pos.model` from pyltp import Postagger postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 result = [] file = [(const.qc_train_seg, const.qc_train_pos), (const.qc_test_seg, const.qc_test_pos)] for i in range(2): with open(file[i][0], 'r', encoding='utf-8') as f: for line in f.readlines(): attr = line.strip().split('\t') words = attr[1].split(" ") words_pos = postagger.postag(words) res = ' '.join([ "{}/_{}".format(words[i], words_pos[i]) for i in range(len(words)) ]) result.append("{}\t{}\n".format(attr[0], res)) with open(file[i][1], 'w', encoding='utf-8') as f: f.writelines(result) result.clear() postagger.release() # 释放模型
class LTP_word(): """docstring for parser_word deal处理文本,返回词表、词性及依存关系,语义,命名实体五个值 release释放缓存""" def __init__(self, model_path): self.model_path = model_path self.segmentor = Segmentor() # 分词初始化实例 self.segmentor.load_with_lexicon(path.join(self.model_path, 'cws.model'), path.join(self.model_path, 'dictionary_kfc.txt')) self.postagger = Postagger() # 词性标注初始化实例 self.postagger.load(path.join(self.model_path, 'pos.model') ) # 加载模型 self.recognizer = NamedEntityRecognizer() # 命名实体识别初始化实例 self.recognizer.load(path.join(self.model_path, 'ner.model')) self.parser = Parser() # 依存句法初始化实例 s self.parser.load(path.join(self.model_path, 'parser.model')) # 加载模型 self.labeller = SementicRoleLabeller() # 语义角色标注初始化实例 self.labeller.load(path.join(self.model_path, 'srl')) def deal (self, text): #把所有该要使用的东西都提取出来 words =self.segmentor.segment(text) # 分词 postags = self.postagger.postag(words) # 词性标注 netags = self.recognizer.recognize(words, postags) #命名实体 arcs = self.parser.parse(words, postags) # 句法分析 roles = self.labeller.label(words, postags, netags, arcs) # 语义角色标注 return words,postags,arcs,roles,netags def release(self): self.segmentor.release() self.postagger.release() self.recognizer.release() self.parser.release() self.labeller.release()
class LtpTree(DepTree): def __init__(self, dict_path=None): super(DepTree, self).__init__() print("正在加载LTP模型... ...") self.segmentor = Segmentor() if dict_path is None: self.segmentor.load(os.path.join(MODELDIR, "cws.model")) else: self.segmentor.load_with_lexicon(os.path.join(MODELDIR, "cws.model"), dict_path) self.postagger = Postagger() self.postagger.load(os.path.join(MODELDIR, "pos.model")) self.parser = Parser() self.parser.load(os.path.join(MODELDIR, "parser.model")) print("加载模型完毕。") def parse(self, sentence): self.words = self.segmentor.segment(sentence) self.postags = self.postagger.postag(self.words) self.arcs = self.parser.parse(self.words, self.postags) for i in range(len(self.words)): if self.arcs[i].head == 0: self.arcs[i].relation = "ROOT" def release_model(self): # 释放模型 self.segmentor.release() self.postagger.release() self.parser.release()
def namedEntityRecognize(sentence): ''' 使用pyltp模块进行命名实体识别 返回:1)命名实体和类别元组列表、2)实体类别列表 ''' namedEntityTagTupleList = [] segmentor = Segmentor() # segmentor.load(inout.getLTPPath(index.CWS)) segmentor.load_with_lexicon(inout.getLTPPath(index.CWS), inout.getResourcePath('userDic.txt')) words = segmentor.segment(sentence) segmentor.release() postagger = Postagger() postagger.load(inout.getLTPPath(index.POS)) postags = postagger.postag(words) postagger.release() recognizer = NamedEntityRecognizer() recognizer.load(inout.getLTPPath(index.NER)) netags = recognizer.recognize(words, postags) recognizer.release() # 封装成元组形式 for word, netag in zip(words, netags): namedEntityTagTupleList.append((word, netag)) neTagList = '\t'.join(netags).split('\t') return namedEntityTagTupleList, neTagList
class NLP: default_model_dir = 'D:\python-file\knowledge_extraction-master-tyz\\ltp_data_v3.4.0\\' #LTP模型文件目录 def __init__(self, model_dir=default_model_dir): self.default_model_dir = model_dir #词性标注模型 self.postagger = Postagger() postag_flag = self.postagger.load( os.path.join(self.default_model_dir, 'pos.model')) def get_postag(self, word): """获得单个词的词性标注 Args: word:str,单词 Returns: pos_tag:str,该单词的词性标注 """ pos_tag = self.postagger.postag([ word, ]) return pos_tag[0] def close(self): """ 关闭与释放 """ self.postagger.release()
class Parse_Util(object): def __init__(self, lexicon_path='./data/lexicon'): # 分词 self.segmentor = Segmentor() # self.segmentor.load_with_lexicon(cws_model_path, lexicon_path) self.segmentor.load(cws_model_path) # 词性标注 self.postagger = Postagger() self.postagger.load(pos_model_path) # 依存句法分析 self.parser = Parser() self.parser.load(par_model_path) # 命名实体识别 self.recognizer = NamedEntityRecognizer() self.recognizer.load(ner_model_path) # jieba 分词 # jieba.load_userdict(lexicon_path) def __del__(self): self.segmentor.release() self.postagger.release() self.recognizer.release() self.parser.release() # 解析句子 def parse_sentence(self, sentence): words = self.segmentor.segment(sentence) postags = self.postagger.postag(words) netags = self.recognizer.recognize(words, postags) arcs = self.parser.parse(words, postags) # child_dict_list = ParseUtil.build_parse_child_dict(words, arcs) return words, postags, netags, arcs
def test_ltp(document): LTP_DATA_DIR = r"D:\anaconda\envs\TF+3.5\Lib\site-packages\pyltp-model" # ltp模型目录的路径 par_model_path = os.path.join( LTP_DATA_DIR, 'parser.model') # 依存句法分析模型路径,模型名称为`parser.model` cws_model_path = os.path.join(LTP_DATA_DIR, 'cws.model') # 分词模型路径,模型名称为`cws.model` pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # 词性标注模型路径,模型名称为`pos.model` segmentor = Segmentor() # 初始化实例 segmentor.load(cws_model_path) # 加载模型 words = segmentor.segment(document) # 分词 print("\nA") print("分词结果:") print('\t'.join(words)) segmentor.release() # 释放模型 postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 postags = postagger.postag(words) # 词性标注 print("\n") print("词性标注结果:") print('\t'.join(postags)) postagger.release() # 释放模型 parser = Parser() # 初始化实例 parser.load(par_model_path) # 加载模型 arcs = parser.parse(words, postags) # 句法分析 print("\n") print("句法分析结果:") print("\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs)) parser.release() # 释放模型
def new_relation_find(words, sentence): """ 新关系发现 :param words: :param sentence: :return: """ # 存放三元组的字典 tuple_dict = dict() index0 = -1 index1 = -1 bool = False for entity_word in entity_words: if sentence.find(entity_word) != -1: if tuple_dict: # 返回为true说明有重复部分 if has_same(tuple_dict[index0], entity_word): continue index1 = sentence.find(entity_word) tuple_dict[index1] = entity_word bool = True break else: index0 = sentence.find(entity_word) tuple_dict[index0] = entity_word if bool is False: return "", "", "" # 排序结果为list # tuple_dict = sorted(tuple_dict.items(), key=lambda d: d[0]) words = "/".join(words).split("/") for key, value in tuple_dict.items(): tuple_word = value words = init_words(tuple_word, words) # 对于已经重构的词进行词标注 postagger = Postagger() # 初始化实例 pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') # 词性标注模型路径,模型名称为`pos.model` postagger.load_with_lexicon(pos_model_path, 'data/postagger.txt') # 加载模型 postags = postagger.postag(words) # 词性标注 print('\t'.join(postags)) postagger.release() # 释放模型 # 发现新关系 relation_word = "" index_word = 0 for index, postag in enumerate('\t'.join(postags).split('\t')): index_word += len(words[index]) if index_word >= len(sentence): break if postag == 'v' and index_word - min(index0, index1) <= 2 and max(index0, index1) - index_word <= 2 \ and not has_same(tuple_dict[index0], words[index]) and not has_same(tuple_dict[index1], words[index]) \ and words[index] not in wrong_relation: relation_word = words[index] break if relation_word == "": return "", "", "" return tuple_dict[min(index0, index1)], tuple_dict[max(index0, index1)], relation_word
class Opinion(object): def __init__(self, Dsent, industry_id): self.industry_id = industry_id self.Dsent = Dsent self.postagger = Postagger() # 初始化实例 self.postagger.load_with_lexicon(pos_model_path, '%s/conf/posttags.txt' % dir_path) self.sql = mysqls() self.opinionword = read_opinion(self.industry_id) self.n_v = [] def cut_word(self, sents): # 分词 words = [i.encode('utf-8', 'ignore') for i in norm_cut(sents)] # HMM=False return words def word_sex(self, ): # 获取词性 postags = list(self.postagger.postag(self.words)) # 词性标注 num = 0 #副词或者名词后面一个词 for tag in postags: if tag in ['d']: if num + 1 < len(postags): if num != 0 and postags[num + 1] in ['n', 'v']: if self.words[num+1] not in self.opinionword \ and len(self.words[num + 1].decode('utf-8','ignore')) > 1: self.n_v.append(self.words[num + 1]) #动词或者n词 if tag in ['a', 'i', 'b']: if self.words[num] not in self.opinionword\ and len(self.words[num].decode('utf-8','ignore')) > 1: self.n_v.append(self.words[num]) num += 1 return postags def prepare(self, ): for id, sentences in self.Dsent.items(): split_sentence = re.split( ur'[,,()()、: …~?。!. !?]?', sentences.decode('utf-8', 'ignore').strip()) for sent in split_sentence: self.words = self.cut_word(sent.encode('utf-8', 'ignore')) self.postags = self.word_sex() cword = Counter(self.n_v) lresult = heapq.nlargest(500, cword.items(), key=lambda x: x[1]) # lword = [] # for rg in lresult: # w, n = rg # lword.append(w) # self.sql.insert(self.industry_id, lword) self.postagger.release() # 释放模型 # self.parser.release() # 释放模型 # outfile.close() return lresult
def ltp_postagger(LTP_DATA_DIR, words): # 词性标注模型路径,模型名称为`pos.model` pos_model_path = os.path.join(LTP_DATA_DIR, 'pos.model') postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 postags = postagger.postag(words) # 词性标注 postagger.release() # 释放模型 return postags
def posttagger(words): postagger = Postagger() # 初始化实例 postagger.load(pos_model_path) # 加载模型 postags = postagger.postag(words) # 词性标注 #for word, tag in zip(words, postags): #print(word + '/' + tag) postagger.release() # 释放模型 return postags
def posttagger(words): postagger = Postagger() # 初始化实例 postagger.load(os.path.join(LTP_DATA_DIR, 'pos.model')) # 加载模型 postags = postagger.postag(words) # 词性标注 for word, tag in zip(words, postags): print(word + '/' + tag) postagger.release() # 释放模型 return postags
def posttagger(words): postagger = Postagger() postagger.load('E:\\git\\ltp-data-v3.3.1\\ltp_datapos.model') posttags = postagger.postag(words) #词性标注 postags = list(posttags) postagger.release() #释放模型 #print type(postags) return postags
def posttagger(words): postagger = Postagger() postagger.load(r'D:\Corpus\ltp_data_v3.4.0\pos.model') posttags = postagger.postag(words) # 词性标注 postags = list(posttags) postagger.release() # 释放模型 # print type(postags) return postags
def pos_tagging(cutting_list): pos_model_path = os.path.join(LtpParser.ltp_path, 'pos.model') from pyltp import Postagger pos_tagger = Postagger() pos_tagger.load(pos_model_path) tags = pos_tagger.postag(cutting_list) pos_tagger.release() return tags
def posttagger(words): postagger = Postagger() postagger.load('D:\\ltp_data\\pos.model') posttags = postagger.postag(words) #词性标注 postags = list(posttags) postagger.release() #释放模型 # print(type(postags)) return postags
def posttagger(words): postagger = Postagger() # 初始化实例 postagger.load( r'D:\SUFE\ComputerContest\QASystem\DrQA-CN-master\data\ltp_data_v3.4.0\pos.model' ) postags = postagger.postag(words) # 词性标注 postagger.release() return postags
def __init__(self): self.cws_model_path = os.path.join(self.LTP_DATA_DIR, 'cws.model') # 分词模型路径,模型名称为`cws.model` self.pos_model_path = os.path.join(self.LTP_DATA_DIR, 'pos.model') # 词性标注模型路径,模型名称为`pos.model` self.ner_model_path = os.path.join(self.LTP_DATA_DIR, 'ner.model') # 命名实体识别模型路径,模型名称为`pos.model` segmentor = Segmentor() segmentor.load(self.cws_model_path) self.words = segmentor.segment(data) # print("|".join(words)) segmentor.release() postagger = Postagger() # 初始化实例 postagger.load(self.pos_model_path) # 加载模型 self.postags = postagger.postag(self.words) # 词性标注 # print('\t'.join(postags)) postagger.release() # 释放模型 recognizer = NamedEntityRecognizer() # 初始化实例 recognizer.load(self.ner_model_path) # 加载模型 self.netags = recognizer.recognize(self.words, self.postags) # 命名实体识别 # print('\t'.join(netags)) recognizer.release() # 释放模型
postagger.load(os.path.join(MODELDIR, "pos.model")) postags = postagger.postag(words) # list-of-string parameter is support in 0.1.5 # postags = postagger.postag(["中国","进出口","银行","与","中国银行","加强","合作"]) print "\t".join(postags) parser = Parser() parser.load(os.path.join(MODELDIR, "parser.model")) arcs = parser.parse(words, postags) print "\t".join("%d:%s" % (arc.head, arc.relation) for arc in arcs) recognizer = NamedEntityRecognizer() recognizer.load(os.path.join(MODELDIR, "ner.model")) netags = recognizer.recognize(words, postags) print "\t".join(netags) labeller = SementicRoleLabeller() labeller.load(os.path.join(MODELDIR, "srl/")) roles = labeller.label(words, postags, netags, arcs) for role in roles: print role.index, "".join( ["%s:(%d,%d)" % (arg.name, arg.range.start, arg.range.end) for arg in role.arguments]) segmentor.release() postagger.release() parser.release() recognizer.release() labeller.release()