open-entity-relation-extraction
open-entity-relation-extraction copied to clipboard
lemonhu
Knowledge triples extraction and knowledge base construction based on dependency syntax for open domain text.
你好，我想做土木工程领域的三元抽取，最开始我以为加入领域词典辅助分词就可以抽取出部分三元组，比如主谓宾形式的三元组，然后看上一个问题的解答才知道，只能抽取人名、机构名、组织名这些类别实体的三元组，请问一下有什么方法可以抽取出土木领域的三元组，比如句子“施工员设置防护栏杆。”程序识别结果如下： 1 施工员 n 2 SBV 2 设置 v 0 HED 3 防护栏杆 n 2 VOB 请问能否通过修改entity_combine.py程序然后抽取出n-v-n的三元组，或者别的什么方法可以抽取类似此类句子的三元组，谢谢。
您好，您在open-entity-relation-extraction/code/core/entity_combine.py 的第55行注释中表明 ` 词合并: (前后词都是实体) and (前后词的词性相同 or 前词 in ["nz", "j"] or 后词 in ["nz", "j"])` 但是在56行和57行代码中，只有设置`前词 in ["nz", "j"] or 后词 in ["nz", "j"]`，并没有设置 `前后词性相同`这一个步骤 ``` if (self.is_entity(word.postag)...
你好，paper中有说用逻辑回归去进行三元组的取舍，但是代码中既没有相关的训练的代码，也没有训练的数据。论文中的Table 7，在论文中也找不到对应的表格。请问这些代码和数据能去哪里获取一下吗？
asking
why i get it? can you tell me how to deal it or explain the reason. thankyou! Building prefix dict from the default dictionary ... Loading model from cache C:\Users\gongh\AppData\Local\Temp\jieba.cache...
Is there any way that we can have the training data(Chinese Corpus that u mentioned on Paper)?
您好！感谢分享！我在运行的时候出现了以下问题（已经load model了）： Start extracting... Building prefix dict from the default dictionary ... Loading model from cache /var/folders/_t/9brcc8tj3jbd5v9455w8bzh80000gp/T/jieba.cache Loading model cost 0.989 seconds. Prefix dict has been built successfully. Traceback (most...
Start extracting... Building prefix dict from the default dictionary ... Loading model from cache C:\Users\z\AppData\Local\Temp\jieba.cache Loading model cost 0.338 seconds. Prefix dict has been built successfully. Process finished with exit...
