tribleave / scapt-absa Goto Github PK
View Code? Open in Web Editor NEWCode for EMNLP 2021 paper: "Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training"
License: MIT License
Code for EMNLP 2021 paper: "Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training"
License: MIT License
作者您好,请问预训练阶段用的yelp和amazon数据集是原始发布的数据集本身就带有aspect信息,还是您采取什么方法标注的,或是其他人的工作标注的呢?
您好,感谢您的工作带给我非常多的思考。
因为想复现一下,所以想知道你在pre-training的时候,使用了多少的Amazon和Yelp数据呢? 文章说manually check a small portion,但是网盘提供的分别是一百万和四百万条数据,请问您在预训练的时候使用部分可以发布一下吗?
另外关于验证集的问题,好像您的代码里面并没有出现验证集?而是直接用的测试集去选取的模型吗?如果是这样的话是否欠妥?
您好,TransEncAsp在Restaurant的valid acc一直在0.70波动,没有您论文写的77.10,请问这是什么情况?谢谢
很感谢您的工作,非常清晰。
想请教一个问题,是否有对比以下两种情况的表现呢:
目前跑了BERTAsp+SCAPT 关于Restaurant的结果 效果差了好几个点 但是直接使用官方公布的权重 效果和论文一模一样
不知道是我自己预训练+微调时哪一步有问题
直接跑代码,在预训练和微调时 都会产生很多checkpoints 我都是选用的最后一个 请问这里有问题吗
你好!我注意到您发布了预训练+下游任务上微调的模型权重,请问您能否发布仅预训练的模型权重(BERT)?
非常感谢你们团队所提出的面向ABSA的对比学习预训练方法。我最近也在做预训练相关的工作。我需要在多个下游任务上对多个预训练模型进行比较,这包括你们提出的模型。但在下游任务上微调过的模型,存在数据泄露的风险。因此,如果您可以提供仅预训练的模型权重(在BERT的基础上在yelp和amazon上预训练的模型权重),我的比较将会更加的公平和客观。
希望得到您的帮助!
hi nice work!
I am wondering where can i got the pretrained models you mentioned? i only find the raw data link for pretrain on readme.
thanks!
jackie
您好,请问可以提供训练好的预训练模型吗,我想复现下代码,谢谢。
作者您好,我使用您提供的预训练好的模型,在微调阶段进行实验,最终复现的数据远不如您在论文中提到的数据
在ISE上,分数最多下降了9个百分点
同时,在lap数据集上,使用您训练好的SCAPT在BERTAsp上的实验结果,会比没有使用SCAPT直接跑BERTAsp上的实验结果低
参数的设置是和您一样的,想请问一下为什么,谢谢!
SCAPT-ABSA/model/module/misc.py
Line 27 in 5f341fd
you add the encoder's [CLS] hidden states to every input word embeddings as transformer decoder's input, which may be not consistent with your claim "hi acts as a beginning- of-sentence input embedding in the decoding process to control the whole generation"
Thanks for you reply in advance!
Hello,
I get the following CUDA error when I run the pre-training code:
CUDA error: CUBLAS_STATUS_INTERNAL_ERROR when calling `cublasCreate(handle)`
I installed requirements, downloaded the data, and followed the pre-training instruction.
Is there a way I could fix this error?
And is there a way I could run the pre-training code in CPU, not GPU?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.