VLP-MABSA

VLP-MABSA copied to clipboard

请问可以开源其他子任务的代码吗？

11

作者您好，我目前在研究相关的方向，对您这篇文章比较感兴趣，想请问您可以开源其他子任务的代码吗，貌似目前的代码只涉及一个下游任务，想再复现一下这篇论文

winder-source

About reproducing KM-BART

1

Hello, I have seen some contents of KM-BART in this article. Have you ever reproduced KM-BART? I met some problems in the process of reproducing, such as the failure to...

getfighting

Faster-RCNN to extract the region feature

6

I would like to know how to use Faster-RCNN to extract the region feature(only retain 36 regions with highest Confidence) as the input feature and the dimension of each region...

sxf97

Questions about how to process the original dataset

5

Nice work and nice repository ! But I still have some doubts about the repository~ 1. Could you please provide some more instructions about how to process the original MVSA...

jc-ryan

how to train on MASC downstream task?

15

hello, I would like to ask if the current code supports the downstream MASC task, because there is a difference between its input and the trunk task input, because the...

BigHyf

about the downstream datasets

1

There are many empty pictures in IJCAI2019_data\twitter2017_images. Could you upload them again  

sen0902

关于transformers 版本问题？

2

请问transformers是必须要用3.4.0版本么？ 实验环境是linux系统么

sydmou

预训练数据集中的 &amp &lt 需要做 unescape 么？

1

您好， 我下载预训练数据后发现里面有一些 &amp , &lt 这样被转义后的token，这些您有做 unescape 么？  感谢

1024er

测试数据中的mask

3

作者您好，为什么测试数据集中也要有mask，我的理解是文本预训练的时候mask可以增强对方面项的辨别。那到测试的数据时候为什么还需要mask掉呢。还是说在测试的时候有对数据的mask部分有特殊处理呢 

yaxxm

复现问题

3

打扰一下，请问这个问题要怎么解决？ OSError: Can't load config for 'bart-base'. Make sure that: - 'bart-base' is a correct model identifier listed on 'https://huggingface.co/models' - or 'bart-base' is the correct path to a directory...

NanZhang257