yixinL7 / SimCLS

Code for our paper "SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization", ACL 2021

yixinL7/SimCLS Issues

关于框架图的疑惑
Updated 2 years ago1
Regarding the results in Table 3
Updated 2 years ago
Can we use pretrained or trained model to generate summarization from our input
Updated 2 years ago
Train set and test set ranking distribution difference
Updated 2 years ago7
Any try on other generation task ?
Closed 2 years ago4
About BS and MS metrics
Updated 2 years ago2
About TotalLoss in model.RankingLoss
Closed 2 years ago2
model.pt question
Updated 2 years ago1
Where are candidate summaries created
Updated 2 years ago1
Example begin dataset
Updated 2 years ago1
Can we change_ Set the batch size value in the setting so that it is not 1
Closed 3 years ago
If I want to create a new dataset (not CNN/DailyMail and XSum) , what should I prepare for it?
Updated 3 years ago1
The difference between loss function and loss code part
Closed 3 years ago3
ERROR: Could not find a version that satisfies the requirement mkl-fft==1.0.15 (from -r requirements.txt (line 48)) (from versions: 1.3.0) ERROR: No matching distribution found for mkl-fft==1.0.15 (from -r requirements.txt (line 48))
Closed 3 years ago2
About CNN/DM and XSum dataset
Closed 3 years ago
On well trained models
Closed 3 years ago4
doubt regarding inputs to preprocess.py
Closed 3 years ago3
code about candidate generation
Closed 3 years ago4
A question in Table 1: Results on CNNDM.
Closed 3 years ago4