argumentpairextraction's People
Contributors
Stargazers
Watchers
argumentpairextraction's Issues
negative sampling
Can you tell me which part of the code adjusts negative sampling? I want to change it.
Question about the annotated data.
Sorry to bother you.
Could you please explain the meaning of the tags in the annotation data file ReviewRebuttalnew2.txt? Especially the labels like 'B-1', 'B-2', 'I-2'.
A question about baseline MT-LSTM-CRF
The MT-LSTM-CRF uses S-LSTM to replace T-LSTM or just removes T-LSTM?
运行问题
如图，torch==1.10.0+cu113 allennlp==2.10.0,请问为啥会出现这个问题呢……
论文里用的是bert-as-service，为什么还要用elmo呢
论文和data_processing的代码里都使用了bert做embedding，但是代码里还有使用elmo，请问原因是啥
question about data process
using GPU... 0
Reading file: data/rr-passage/train.txt
FileNotFoundError Traceback (most recent call last)
/deepo_data/APE/trainer.py in
314
315 if name == "main":
--> 316 main()
/deepo_data/APE/trainer.py in main()
283 set_seed(opt, conf.seed)
284
--> 285 trains = reader.read_txt(conf.train_file, conf.train_num)
286 devs = reader.read_txt(conf.dev_file, conf.dev_num)
287 tests = reader.read_txt(conf.test_file, conf.test_num)
/deepo_data/APE/config/reader.py in read_txt(self, file, number)
27
28 # f_vec = open(file[:8]+'vec_test.pkl', 'rb')
---> 29 f_vec = open(file[:8] + 'vec_' + file[8:-3] + 'pkl', 'rb')
30 all_vecs = pickle.load(f_vec)
31 f_vec.close
FileNotFoundError: [Errno 2] No such file or directory: 'data/rr-vec_passage/train.pkl'
Could you please provide the dataset with different difficulty levels？
In Section 6.3.1 of your paper, the author analyzed comparison among different difficulty levels, which I think is very important. So, could you please provide the dataset with different difficulty levels？
ReviewRebuttalnew2.txt
Sorry to bother you. I didn't find the ReviewRebuttalnew2.txt file in this repo. Would you please tell me where I can download it? Thanks a lot!
could you please tell me the version of allennlp...
run in the enviroment
torch==1.10.0+cu113 torchvision==0.11.0+cu113 allennlp==2.10.0
this mistake happened when I run trainer.py
bug
There are still some problems.
in reader.py :
type_id = 1
if line_idx<len(f)-2:
#print(f[line_idx+2].rstrip().split('\t'))
if label[0] != 'O' or (label[0]=='O' and ( (new_index>0 and f[line_idx-1].rstrip().split('\t')[1][0] != 'O') or
(new_index>1 and f[line_idx-2].rstrip().split('\t')[1][0] != 'O') or
(f[line_idx+1]!='' and f[line_idx+1].rstrip().split('\t')[1][0] != 'O') or
(f[line_idx+1]!='' and f[line_idx+2]!='' and f[line_idx+2].rstrip().split('\t')[1][0] != 'O' ))):
reply_idx.append(sent_idx)
elif line_idx==len(f)-2:
if f[line_idx + 1].rstrip() != '':
if label[0] != 'O' or (label[0] == 'O' and (
(new_index > 0 and f[line_idx - 1].rstrip().split('\t')[1][0] != 'O') or
(new_index > 1 and f[line_idx - 2].rstrip().split('\t')[1][0] != 'O') or
(f[line_idx + 1] != '' and f[line_idx + 1].rstrip().split('\t')[1][0] != 'O'))):
reply_idx.append(sent_idx)
else:
if label[0] != 'O' or (label[0] == 'O' and (
(new_index > 0 and f[line_idx - 1].rstrip().split('\t')[1][0] != 'O') or
(new_index > 1 and f[line_idx - 2].rstrip().split('\t')[1][0] != 'O'))):
reply_idx.append(sent_idx)
elif line_idx==len(f)-1:
if label[0] != 'O' or (label[0]=='O' and ( (new_index>0 and f[line_idx-1].rstrip().split('\t')[1][0] != 'O') or
(new_index>1 and f[line_idx-2].rstrip().split('\t')[1][0] != 'O'))):
reply_idx.append(sent_idx)
I found that len(f)=160090. line_idx<len(f)-2 often ture. However f[line_idx+2].rstrip().split('\t')[1][0] != 'O' and f[line_idx+2].rstrip().split('\t')[1][0] != 'O' happens index error (f[line_idx+2] or f[line_idx+1] is '').
RR-submission-v2标签不一致问题
图片里的数字为什么“1.”标签是“I-Reply I-1”而“2.”却是“O O”
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.