-
## Expected Behavior
Most of the expected values vs observed values in the `keyterms.sgrank` should match even though some may be different due to randomness of the results. `keyterms.textrank` a…
-
Due to an [issue in spaCy](https://github.com/explosion/spaCy/issues/719), textrank can return the empty string as a key term for a document. This is due to spaCy sometimes lemmatizing the string 's' …
-
Running the following code from the Python REPL has no issue at all.
from textrankr import TextRank
textrank = TextRank('Some text')
textrank.summarize()
However, running it from…
-
example; 有段文字提取后的summary=“提出来一种全新的研究方案”
该句被作为textrank高分值输出，但是因为没有主语, 而容易造成误解.
请问是否有什么方法 可以得到上下文相关的主语?
Thanks & BR
Andy
-
This may be related to [Issue #181](https://github.com/nystudio107/seomatic/issues/181) but I'm opening a new issue since I have a specific error message.
We configured an SEOmatic field to automat…
-
该项目有没有一个todo list 呢；
很想知道下一步以及以后的规划
还请问一下，有没有计划做 实体识别、文本分类的功能；
此外目前的关键词提取还是有些不够准确，有没有计划考虑集成 TF/IDF 进行完善呢
-
Hi, I am trying to use networkx's PageRank algorithm for my implementation of TextRank.
https://web.eecs.umich.edu/~mihalcea/papers/mihalcea.emnlp04.pdf
The scoring matrix that they have used uses wei…
-
Hi,
I followed all the steps in the example section but the textacy.keyterms.textrank(doc, n_keyterms=10) function returns the following error:
ValueError: token is not POS-tagged
The error is raise…
-
Tried to install and run example as detailed on README, and encountered this error:
`Traceback (most recent call last):
File "stage1.py", line 5, in
import textrank
File "/Users/mattkohl/Dev…
-
我找到一篇名为：TextRank: Bringing Order into Texts
但里面的TextRank提取关键词的方法是以词性作为考量的，而您的算法是 权重是 1/连接总数，即所有和中心词连接的其他词均分这个影响力。
请问你这么是按照这篇文章来的吗？还是按照其他文章来的？