Writing

NLP (5) — Open Chinese Entity–Relation Extraction via Dependency Parsing

NLP-focused notes on dependency-based open entity–relation extraction in Chinese.

Preface: This article is filed under NLP because it mainly covers NLP topics. Prior reading:

pyltp — HIT Language Cloud Python interface: https://www.jianshu.com/p/867478f0e674
Open Chinese entity–relation extraction via dependency parsing, Li Mingyao (searchable on Baidu)
Example: https://github.com/twjiang/fact_triple_extraction
Zheng Shanshan — Open-domain entity–relation extraction based on Chinese syntactic features

Environment Setup

Install pyltp: 1) If pip fails, adjust the version. 2) Download the matching model from http://ltp.ai/download.html

Prior Work

Bootstrapping enables semi-supervised distant relation extraction: seed templates extract feature words; nearest-neighbor rules auto-generate more templates. During expansion, incorrect templates accumulate and errors compound, hurting final quality.

Extracting Triples

Pipeline: segmentation → POS tagging → NER (person, place, organization only; tag others manually) → dependency parsing. Overview:

Reference: https://www.ltp-cloud.com/intro/#ner_how

Code:

Loading models:

segmentor = Segmentor()
segmentor.load(os.path.join(MODELDIR, "cws.model"))

postagger = Postagger()
postagger.load(os.path.join(MODELDIR, "pos.model"))

parser = Parser()
parser.load(os.path.join(MODELDIR, "parser.model"))

recognizer = NamedEntityRecognizer()
recognizer.load(os.path.join(MODELDIR, "ner.model"))

Core relation extraction:

for index in range(len(postags)):
        # 抽取以谓词为中心的事实三元组
        if postags[index] == 'v':
            child_dict = child_dict_list[index]
            # 主谓宾
            if child_dict.__contains__('SBV') and child_dict.__contains__('VOB'):
                e1 = complete_e(words, postags, child_dict_list, child_dict['SBV'][0])
                r = words[index]
                e2 = complete_e(words, postags, child_dict_list, child_dict['VOB'][0])
                out_file.write("主语谓语宾语关系\t(%s, %s, %s)\n" % (e1, r, e2))
                print(e1,r,e2)
                out_file.flush()
            # 定语后置，动宾关系
            if arcs[index].relation == 'ATT':
                if child_dict.__contains__('VOB'):
                    e1 = complete_e(words, postags, child_dict_list, arcs[index].head - 1)
                    r = words[index]
                    e2 = complete_e(words, postags, child_dict_list, child_dict['VOB'][0])
                    temp_string = r+e2
                    if temp_string == e1[:len(temp_string)]:
                        e1 = e1[len(temp_string):]
                    if temp_string not in e1:
                        out_file.write("定语后置动宾关系\t(%s, %s, %s)\n" % (e1, r, e2))
                        out_file.flush()
            # 含有介宾关系的主谓动补关系
            if child_dict.__contains__('SBV') and child_dict.__contains__('CMP'):
                #e1 = words[child_dict['SBV'][0]]
                e1 = complete_e(words, postags, child_dict_list, child_dict['SBV'][0])
                cmp_index = child_dict['CMP'][0]
                r = words[index] + words[cmp_index]
                if child_dict_list[cmp_index].__contains__('POB'):
                    e2 = complete_e(words, postags, child_dict_list, child_dict_list[cmp_index]['POB'][0])
                    out_file.write("介宾关系主谓动补\t(%s, %s, %s)\n" % (e1, r, e2))
                    out_file.flush()

        # 尝试抽取命名实体有关的三元组
        if netags[index][0] == 'S' or netags[index][0] == 'B':
            ni = index
            if netags[ni][0] == 'B':
                while netags[ni][0] != 'E':
                    ni += 1
                e1 = ''.join(words[index:ni+1])
            else:
                e1 = words[ni]
            if arcs[ni].relation == 'ATT' and postags[arcs[ni].head-1] == 'n' and netags[arcs[ni].head-1] == 'O':
                r = complete_e(words, postags, child_dict_list, arcs[ni].head-1)
                if e1 in r:
                    r = r[(r.index(e1)+len(e1)):]
                if arcs[arcs[ni].head-1].relation == 'ATT' and netags[arcs[arcs[ni].head-1].head-1] != 'O':
                    e2 = complete_e(words, postags, child_dict_list, arcs[arcs[ni].head-1].head-1)
                    mi = arcs[arcs[ni].head-1].head-1
                    li = mi
                    if netags[mi][0] == 'B':
                        while netags[mi][0] != 'E':
                            mi += 1
                        e = ''.join(words[li+1:mi+1])
                        e2 += e
                    if r in e2:
                        e2 = e2[(e2.index(r)+len(r)):]
                    if r+e2 in sentence:
                        out_file.write("人名//地名//机构\t(%s, %s, %s)\n" % (e1, r, e2))
                        out_file.flush()