renj / pseudo-ref Goto Github PK

Thanks for this code .

When using the following sentences as dataset , I met a infinite loop in dfs(G, T, u, visited) :

伦敦 每日 快报 指出 , 两 台 记载 黛安娜 王妃 一九九七年 巴黎 死亡 车祸 调查 资料 的 手提 电脑 , 被 从前 大都会 警察 总 长 的 办公室 里 偷走 。
london 's daily express noted that two laptops with inquiry data on the 1997 paris car accident that caused the death of princess diana were stolen from the office of a former metropolitan police commissioner .
london daily express pointed out that two laptop computers , which contain investigation materials about the car accident and death of princess diana in 1997 , were stolen from the office of the former metropolitan police chief .
london 's daily express has reported that two laptop computers containing material on the probe into princess diana 's fatal car crash in paris in 1997 have been stolen from the office of a former metropolitan police commissioner .
the london daily indicated that two laptop computers containing investigative materials on the 1997 paris car accident and death of princess diana were stolen from the office of the former commissioner of the metropolitan police .
[Quoted from NIST2006 the third sentence]

By the way , I didn't delete punctuation in sentences[tokens]
Then I run this :

python lattice.py -order_method hard -align_method hard -dataset data/dataset.json -minus 0.5

Howerver it is in an infinite loop . I do not know where is wrong .
Hope for your reply . Thank you .

Thanks for this code.

First, the README is missing two dependencies: matplotlib and scipy.

When running the command from the README, I get an error:

Traceback (most recent call last):
File "lattice.py", line 2, in
import msa_class
File "/home/nlp/amit/pseudo-ref/msa_class.py", line 15, in
import loader
ImportError: No module named loader

I am assuming that that is because of

sys.path.append('../pytorch-examples/word_language_model/')

But I haven't found any indication in https://github.com/pytorch/examples/tree/master/word_language_model of a loader.

Can you please add instructions on how to get loader? or maybe add it to this repo as well?