-
Hi,
We are using paraphrase-distilroberta-base-v1 for paraphrase identification. Thanks for the work. It gives good results on many tasks.
Can you kindly share or point me to the source for the d…
-
I fine-tuned t5-large for paraphrase generation for 2 epoches and the paraphrases generated looks good. When I trained for 11 epochs and the model seems overfitted (the paraphrases generated is simila…
-
What is the difference between **Paraphrase Identification** and **Semantic Textual Similarity** ?
And is there a pre-trained model available for Semantic Textual similarity for the Portuguese lang…
-
If I read the PAWS paper correctly, it stated that BiLSTM+cosine similarity is one of the baseline models that was used to evaluate the PAWS dataset. I tried to reenact the experiment with a BiLSTM+co…
-
Statistics:
1. Brief overview of datasets - different parts/subsets/files
2. Datasets size - size of training, test and dev sets
3. Different classes of labels and their counts
4. Sample data (20 …
-
## Paraphrasing
- [ ] https://huggingface.co/tuner007/pegasus_paraphrase
- [ ] https://huggingface.co/kalpeshk2011/dipper-paraphraser-xxl
## Question Rewriting
- [ ] https://github.com/Orange-Op…
-
Paraphrasing is very similar to sentence similarity, but with the crucial difference that it's on longer pieces of text.
Model fine-tuned on Microsoft Research Paraphrase Corpus should do it.
-
论文作者在测试集上的准确率也只有86%，请问如何能达到99%的准确率？我能想到的办法大概是写一个GAN生成更多训练数据。
-
**ACL2018**
- [Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network](https://www.aclweb.org/anthology/P18-1103): Xiangyang Zhou, Lu Li, Daxiang Dong, Yi Liu, Ying Chen, W…
-
1. text
- paraphrase
- q/a
- translation
- summarization
2. image
3. audio