-
Hello, thanks for your works.
I got the final F1 result 82.0% after 5 epoch training while 89.25% in the paper. What about you?
-
in KP-Miner method when compute candidate_weighting all the candidate are multiplied by a fixed number ( B boosting factor). Shouldn't this factor be calculated for unigram phrase only ? and df compu…
-
Hi! I'm bothering you again ...
I recently read your paper and try to reproduce your results. The result for SemEval-2010 Task 1 in your paper is as follows:
![semeval 2010 result](https://user-im…
-
Thank you for your sharing. We are very fortunate to have such a responsible author. Before you release the code for SemEval 2010 Task8, I want to know how you obtain the dependency information for it…
-
## 🚀 Feature
An implementation of the R-BERT architecture for relationship classification
## Motivation
Hi @Huggingface. A recent paper describes an architecture for relationship classificati…
-
很抱歉打扰您，我在运行中出现文件缺失的报错，
不知道能否方便告知我这个data/raw_data/2010_random_filtered.json和2010_full_filtered.json文件是如何获得？
冒昧打扰，还望海涵，期待您的回信
-
### Problems
We observed a significant performance loss. Possible causes:
- Reduction of the batch size from 32 down to 8
- Changing from pairwise to sentence wise train-dev-test splits (major c…
-
Hello! I met a problem when I typed the command:
> cmake .. -DEIGEN3_INCLUDE_DIR=eigen -DCMAKE_CXX_COMPILER=/usr/bin/clang++
The message was:
> ~/LSTM-ER/build$ cmake .. -DEIGEN3_INCLUDE_DIR=../eig…
-
It iteration 100 times ,the best train result in 65 iteration .
I use the SemEval2010_task8_all_data data
-
I downloaded Trained Models to produce your paper results. However, for SemEval2010 Task 8, it is an error when evaluating:
File "/var/autofs/cl/work/TRE-master/train_utils.py", line 97, in load_mo…