-
The paper ACL2022-DuLeMon is very impressing, waiting for open-source data and code.
-
## 몇가지 추가해보자
- Contextual Representation Learning beyond Masked Language Modeling
- ACL2022
- https://aclanthology.org/2022.acl-long.193/
-
Hi, this is very great work. Congrats on being accepted by ACL2022.
But I have a question about the DST model. It seems that the DST model is trained and evaluated on delexicalized response. Howeve…
-
Pre-training：
1. Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering（ACL2022）
2. RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Langua…
-
Hello! Have you successfully reproduced the results of all variants in this paper? After fixing a random seed, are the results reproducible every time?
-
您好，最近在做对话任务方面的研究，通过读到"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory"这篇paper链接到这个repo，请问预计什么时候开源demo提供学习？
-
PersonaExtractor从首次对话中提取相关的个性化信息，但是我发现你们公开的数据中，没有一次对话的原文，取之而代的是已经提取好的个性化信息
-
Hi @paroma ,
Your paper seems interesting !
In the github repository, you have only provided IMDB dataset as a refernce. Could you provide Twitter and CDR data (with relevant pre-processing script…
-
Tasks:
- [x] Take notes in the meetings for the final presentation @SimonP07
- [x] setup file to structure presentation in google drive
- [x] outline the general structure of the final presentatio…
-
你好，我在看代码是发现rel_feature.npy等.npy文件是先前就已生成的，但这样就无法更改数据集，这些是如何生成的？
mxq15 updated
7 months ago