songyouwei / absa-pytorch

Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析，使用PyTorch实现。

ABSA-PyTorch

Aspect Based Sentiment Analysis, PyTorch Implementations.

基于方面的情感分析，使用PyTorch实现。

Requirement

• pytorch >= 0.4.0
• numpy >= 1.13.3
• sklearn
• python 3.6 / 3.7
• transformers

To install requirements, run pip install -r requirements.txt.

• For non-BERT-based models, GloVe pre-trained word vectors are required, please refer to data_utils.py for more detail.

Usage

Training

python train.py --model_name bert_spc --dataset restaurant

• All implemented models are listed in models directory.
• See train.py for more training arguments.
• Refer to train_k_fold_cross_val.py for k-fold cross validation support.

Inference

• Refer to infer_example.py for both non-BERT-based models and BERT-based models.

Tips

• For non-BERT-based models, training procedure is not very stable.
• BERT-based models are more sensitive to hyperparameters (especially learning rate) on small data sets, see this issue.
• Fine-tuning on the specific task is necessary for releasing the true power of BERT.

Framework

For flexible training/inference and aspect term extraction, try PyABSA, which includes all the models in this repository.

Reviews / Surveys

Qiu, Xipeng, et al. "Pre-trained Models for Natural Language Processing: A Survey." arXiv preprint arXiv:2003.08271 (2020). [pdf]

Zhang, Lei, Shuai Wang, and Bing Liu. "Deep Learning for Sentiment Analysis: A Survey." arXiv preprint arXiv:1801.07883 (2018). [pdf]

Young, Tom, et al. "Recent trends in deep learning based natural language processing." arXiv preprint arXiv:1708.02709 (2017). [pdf]

BERT-based models

BERT-ADA (official)

Rietzler, Alexander, et al. "Adapt or get left behind: Domain adaptation through bert language model finetuning for aspect-target sentiment classification." arXiv preprint arXiv:1908.11860 (2019). [pdf]

BERR-PT (official)

Xu, Hu, et al. "Bert post-training for review reading comprehension and aspect-based sentiment analysis." arXiv preprint arXiv:1904.02232 (2019). [pdf]

ABSA-BERT-pair (official)

Sun, Chi, Luyao Huang, and Xipeng Qiu. "Utilizing bert for aspect-based sentiment analysis via constructing auxiliary sentence." arXiv preprint arXiv:1903.09588 (2019). [pdf]

LCF-BERT (lcf_bert.py) (official)

Zeng Biqing, Yang Heng, et al. "LCF: A Local Context Focus Mechanism for Aspect-Based Sentiment Classification." Applied Sciences. 2019, 9, 3389. [pdf]

AEN-BERT (aen.py)

Song, Youwei, et al. "Attentional Encoder Network for Targeted Sentiment Classification." arXiv preprint arXiv:1902.09314 (2019). [pdf]

BERT for Sentence Pair Classification (bert_spc.py)

Devlin, Jacob, et al. "Bert: Pre-training of deep bidirectional transformers for language understanding." arXiv preprint arXiv:1810.04805 (2018). [pdf]

Non-BERT-based models

ASGCN (asgcn.py) (official)

Zhang, Chen, et al. "Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks." Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. 2019. [pdf]

MGAN (mgan.py)

Fan, Feifan, et al. "Multi-grained Attention Network for Aspect-Level Sentiment Classification." Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018. [pdf]

AOA (aoa.py)

Huang, Binxuan, et al. "Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks." arXiv preprint arXiv:1804.06536 (2018). [pdf]

TNet (tnet_lf.py) (official)

Li, Xin, et al. "Transformation Networks for Target-Oriented Sentiment Classification." arXiv preprint arXiv:1805.01086 (2018). [pdf]

Cabasc (cabasc.py)

Liu, Qiao, et al. "Content Attention Model for Aspect Based Sentiment Analysis." Proceedings of the 2018 World Wide Web Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2018.

RAM (ram.py)

Chen, Peng, et al. "Recurrent Attention Network on Memory for Aspect Sentiment Analysis." Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017. [pdf]

MemNet (memnet.py) (official)

Tang, Duyu, B. Qin, and T. Liu. "Aspect Level Sentiment Classification with Deep Memory Network." Conference on Empirical Methods in Natural Language Processing 2016:214-224. [pdf]

IAN (ian.py)

Ma, Dehong, et al. "Interactive Attention Networks for Aspect-Level Sentiment Classification." arXiv preprint arXiv:1709.00893 (2017). [pdf]

ATAE-LSTM (atae_lstm.py)

Wang, Yequan, Minlie Huang, and Li Zhao. "Attention-based lstm for aspect-level sentiment classification." Proceedings of the 2016 conference on empirical methods in natural language processing. 2016.

TD-LSTM (td_lstm.py, tc_lstm.py) (official)

Tang, Duyu, et al. "Effective LSTMs for Target-Dependent Sentiment Classification." Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 2016. [pdf]

LSTM (lstm.py)

Hochreiter, Sepp, and Jürgen Schmidhuber. "Long short-term memory." Neural computation 9.8 (1997): 1735-1780. [pdf]

Note on running with RTX30*

If you are running on RTX30 series there may be some compatibility issues between installed/required versions of torch, cuda. In that case try using requirements_rtx30.txt instead of requirements.txt.

Contributors

Thanks goes to these wonderful people:

Alberto Paz 💻	jiangtao 💻	WhereIsMyHead 💻	songyouwei 💻	YangHeng 💻	rmarcacini 💻	Yikai Zhang 💻
Alexey Naiden 💻	hbeybutyan 💻	Pradeesh 💻

This project follows the all-contributors specification. Contributions of any kind welcome!

Licence

MIT

absa-pytorch's Issues

Bad predictions of the models

Try to input first:
trump is good, but obama is bad, with trump being target.
Then, second with obama being target.
None of the models achieve the result they claim to achieve, because they output the same sentiment for both sentences.
(Sorry if wrongly tested, but i think i didn't).

SqueezeEmbedding 层

Traceback (most recent call last):
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 479, in
train()
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 475, in train
ins.run()
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 403, in run
best_model_path = self._train(criterion, optimizer, train_data_loader, val_data_loader) # 保存最好的模型
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 327, in _train
outputs = self.model(inputs)
File "/Users/wei/anaconda3/envs/tensorflow/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 218, in forward
target = self.squeeze_embedding(target, target_len)
File "/Users/wei/anaconda3/envs/tensorflow/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/Users/wei/Desktop/pythonDemo/nlpdazuoye/nlp_absa/demo2.py", line 70, in forward
x_emb_p = torch.nn.utils.rnn.pack_padded_sequence(x, x_len, batch_first=self.batch_first)
File "/Users/wei/anaconda3/envs/tensorflow/lib/python3.6/site-packages/torch/nn/utils/rnn.py", line 268, in pack_padded_sequence
torch._C._VariableFunctions._pack_padded_sequence(input, lengths, batch_first)
RuntimeError: Length of all samples has to be greater than 0, but found an element in 'lengths' that is <= 0

这种错误 不知道怎么回事

Result reproducing

Thank you very much for implementing the models, but I have a question. Have you tried to reproduce the results on the datasets from the articles with your models?

Attribute error

Multi-Head Attention计算时不考虑位置编码？

请问在Multi-Head Attention计算时不考虑位置编码吗？我在代码中好像没找到，位置编码应该挺重要的吧

'Killed' message during Training after epoch 0:

Could someone please help me to come out of this issue:
I am using miniconda, tried to execute the sentiment analysis, i could see killed message.
Here are the more details:

(base) renuk@renuk-ThinkPad-X1-Carbon-6th:/ABSA-PyTorch$ python -c "import torch; print(torch.version)"
1.0.1.post2
(base) renuk@renuk-ThinkPad-X1-Carbon-6th:/ABSA-PyTorch$ python
Python 3.6.2 |Anaconda, Inc.| (default, Oct 5 2017, 07:59:26)
[GCC 7.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.

[4]+ Stopped python
(base) renuk@renuk-ThinkPad-X1-Carbon-6th:~/ABSA-PyTorch$ python train.py --model_name bert_spc --dataset restaurant --logdir bert_spc_logs
n_trainable_params: 109484547, n_nontrainable_params: 0

training arguments:

model_name: bert_spc
dataset: restaurant
optimizer: <class 'torch.optim.adam.Adam'>
initializer: <function xavier_uniform_ at 0x7f65dd9719d8>
learning_rate: 2e-05
dropout: 0.1
l2reg: 0.01
num_epoch: 20
batch_size: 64
log_step: 5
logdir: bert_spc_logs
embed_dim: 300
hidden_dim: 300
bert_dim: 768
pretrained_bert_name: bert-base-uncased
max_seq_len: 80
polarities_dim: 3
hops: 3
device: cpu
model_class: <class 'models.bert_spc.BERT_SPC'>
dataset_file: {'train': './datasets/semeval14/Restaurants_Train.xml.seg', 'test': './datasets/semeval14/Restaurants_Test_Gold.xml.seg'}
inputs_cols: ['text_bert_indices', 'bert_segments_ids']

epoch: 0
Killed

如何计算模型的运行时间

哈喽，请问如何计算单个模型的运行时间然后与其他模型进行比较呢？谢谢~

在restaurant, laptop数据集报错 could not broadcast input array from shape (25) into shape (300)

How to analyse sentiment according to the aspect term using infer_example.py?

HI,

In the file infer_example.py, I have the following code

def evaluate(self, raw_texts):\n ......\n aspect_seqs = [self.tokenizer.text_to_sequence('battery')] * len(raw_texts)\n ......

t_probs = inf.evaluate(['laptop is good but battery is bad'])\n print(t_probs.argmax(axis=-1) - 1)

why is the sentiment score = 1?

I tested the sentence 'laptop is good' and 'battery is bad and the output are 1 and -1 respectively. But when I combine the sentence together, the output is always 1 no matter the aspect term.

The model I am using is AOA, and it is trained on the laptop reviews and the accuracy is 0.7304.

Why comment out the locationed_memory in memnet and ram

MAGN

您好，在magn模型中，损失函数是不一样的，代码中有体现吗？

The dataset

Please, I want to ask you about the .seg files, how can I convert my dataset to be with this extension?

Thanks,

Error while running infer_example.py for bert_spc

Hi,

I am getting below error when running infer_example.py for bert_spc. Can someone help me solve it?

Below is the code for infer_example.py that I am using.

import torch
import torch.nn.functional as F
import torch.nn as nn
import argparse

from data_utils import build_tokenizer, build_embedding_matrix
from models import IAN, MemNet, ATAE_LSTM, AOA
from models.bert_spc import BERT_SPC


class Inferer:
    """A simple inference example"""

    def __init__(self, opt):
        self.opt = opt
        self.tokenizer = build_tokenizer(
            fnames=[opt.dataset_file['train'], opt.dataset_file['test']],
            max_seq_len=opt.max_seq_len,
            dat_fname='{0}_tokenizer.dat'.format(opt.dataset))
        embedding_matrix = build_embedding_matrix(
            word2idx=self.tokenizer.word2idx,
            embed_dim=opt.embed_dim,
            dat_fname='{0}_{1}_embedding_matrix.dat'.format(str(opt.embed_dim), opt.dataset))
        self.model = opt.model_class(embedding_matrix, opt)
        print('loading model {0} ...'.format(opt.model_name))
        self.model.load_state_dict(torch.load(opt.state_dict_path))
        self.model = self.model.to(opt.device)
        # switch model to evaluation mode
        self.model.eval()
        torch.autograd.set_grad_enabled(False)

    def evaluate(self, raw_texts):
        context_seqs = [self.tokenizer.text_to_sequence(raw_text.lower().strip()) for raw_text in raw_texts]
        aspect_seqs = [self.tokenizer.text_to_sequence('null')] * len(raw_texts)
        context_indices = torch.tensor(context_seqs, dtype=torch.int64).to(self.opt.device)
        aspect_indices = torch.tensor(aspect_seqs, dtype=torch.int64).to(self.opt.device)

        t_inputs = [context_indices, aspect_indices]
        t_outputs = self.model(t_inputs)

        t_probs = F.softmax(t_outputs, dim=-1).cpu().numpy()
        return t_probs


if __name__ == '__main__':
    model_classes = {
        'atae_lstm': ATAE_LSTM,
        'ian': IAN,
        'memnet': MemNet,
        'aoa': AOA,
        'bert_spc': BERT_SPC,
    }
    # set your trained models here
    model_state_dict_paths = {
        'atae_lstm': 'state_dict/atae_lstm_restaurant_acc0.7786',
        'ian': 'state_dict/ian_restaurant_acc0.7911',
        'memnet': 'state_dict/memnet_restaurant_acc0.7911',
        'aoa': 'state_dict/aoa_restaurant_acc0.8063',
        'bert_spc': 'state_dict/bert_spc_restaurant_val_acc0.8196',
    }

    class Option(object):
        pass
    opt = Option()
    opt.model_name = 'bert_spc'
    opt.model_class = model_classes[opt.model_name]
    opt.dataset = 'restaurant'
    opt.dataset_file = {
        'train': './datasets/semeval14/Restaurants_Train.xml.seg',
        'test': './datasets/semeval14/Restaurants_Test_Gold.xml.seg'
    }
    opt.state_dict_path = model_state_dict_paths[opt.model_name]
    opt.embed_dim = 300
    opt.hidden_dim = 300
    opt.max_seq_len = 80
    opt.polarities_dim = 3
    opt.dropout = 0.1
    opt.bert_dim = 768
    opt.hops = 3
    opt.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    inf = Inferer(opt)
    t_probs = inf.evaluate(['happy memory', 'the service is terrible', 'just normal food'])
    print(t_probs.argmax(axis=-1) - 1)

Thanks

The experimental results

Hello,
please, when I run these models using the provided data-sets almost the results were lower than the reported in the original papers by 2 or 3. So, have you any explanation about that?

Thanks a lot,

can't get the same accuracy in the paper

Hi,
Thank you for your modification of the error. I try to run the aen model, and I get 0.7642... after 50 epoch, I am wondering why.
I will be grateful if I can get your reply.

IAN模型的实现

关于IAN模型的实现，

aspect_len = torch.tensor(aspect_len, dtype=torch.float).to(self.opt.device)
aspect = torch.sum(aspect, dim=1)
aspect = torch.div(aspect, aspect_len.view(aspect_len.size(0), 1))
text_raw_len = torch.tensor(text_raw_len, dtype=torch.float).to(self.opt.device)
context = torch.sum(context, dim=1)
context = torch.div(context, text_raw_len.view(text_raw_len.size(0), 1))
aspect_final = self.attention_aspect(aspect, context).squeeze(dim=1)
context_final = self.attention_context(context, aspect).squeeze(dim=1)

在上面的实现中，context 和aspect 最后均为平均值，是否与原文模型不符。

no backward() in CrossEntropyLoss_LSR

I tried to use CrossEntropyLoss_LSR, but i got this error:
AttributeError: 'CrossEntropyLoss_LSR' object has no attribute 'backward'

问一下，文中这个attention权值可视化怎么来的

Is there a validation mechanism in the code ?

Thanks for sharing and making all ABSA baselines together.
Is there a validation mechanism in the code? I am not sure how to know which model (selection) to test.

Test accuracy remain at 0.65

After cloning, I ran the following command

python train.py --model_name bert_spc --dataset restaurant --learning_rate 2e-5 --logdir bert_spc_logs

epoch:  10
loss: 0.9447, acc: 0.6562, test_acc: 0.6500, f1: 0.2626
loss: 0.9312, acc: 0.6562, test_acc: 0.6500, f1: 0.2626
loss: 1.0388, acc: 0.6042, test_acc: 0.6500, f1: 0.2626
loss: 0.9838, acc: 0.5977, test_acc: 0.6500, f1: 0.2626
loss: 0.9509, acc: 0.6000, test_acc: 0.6500, f1: 0.2626
loss: 0.9240, acc: 0.6068, test_acc: 0.6500, f1: 0.2626
loss: 0.8728, acc: 0.6205, test_acc: 0.6500, f1: 0.2626
loss: 1.0066, acc: 0.6113, test_acc: 0.6500, f1: 0.2626
loss: 0.9481, acc: 0.6111, test_acc: 0.6500, f1: 0.2626
loss: 0.9346, acc: 0.6125, test_acc: 0.6500, f1: 0.2626
loss: 0.9435, acc: 0.6122, test_acc: 0.6500, f1: 0.2626

The test accuracy remains at 0.65 and doest not change.

Out of memory

I use a 12GB titanxp. It runs out of memory.
How to avoid this problem ? Is there a bug or my gpu memory is too small? What gpu do you use ?
Thank you

experimental results

请问一下，直接运行你的aen模型，参数不断调整但是f1总是只有0.6左右，最多只有0.65，实在调不到你的水平，可以将你修改的参数值发一下吗，参考一下，谢谢了

How to prepare my own text classification dataset?

Hello authors, thank you for the nice, clean, running repo!
If I want to use the models to my own text classification dataset, what's the best way to prepare the data?
Specifically,

1. What is the best way to mask the aspects with $T$?
   Currently what I have are just plain text and their labels.

2. Is there any way to use AEN_bert or BERT_spc without having to preprocess the data with $T$?

大佬发论文的速度真是叹为观止

动手能力太差，想到做不出来，请问大佬后期对ABSA有更深入研究的打算吗？

I think position embedding is important in sentiment analysis. Maybe adding position embdding in embedding layer makes figure more precise.

I try to modify data_util.py, but there are some places that make me confused. I am caught in the bottleneck. So how to modify data_util.py to add position embedding?
Thanks

Hi~ 一直有个问题想问一下哈...

假如每个句子有不等个target（1-3个），需要预测出来每一个target的情感。。
想问下一下 假如每一个句子target不等的话，如何对齐呢...

我看好多论文最后都是过了softmax，这样的话是只能预测一个target的情感态度吗..

可视化

您好，论文后面可视化图是怎么做的呢

想问一下 大家的网络图都是用什么工具画的呀...

how to run a bert-based model

after install the pytorch-pretrained-bert 0.6.1, and loading vocabulary file https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt , it shows:
https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased.tar.gz not found in cache, downloading to /tmp/tmpzqs03pcr
want to know whether I can install the tar.gz in advance? and how?

关于测试间隔的设置

您好，最近我在跑您基于 BERT 的 AEN 的代码，我发现您在训练的过程中是每间隔 5 个 step 就在测试集上进行一次测试，总共 20 个 epoch，那么这个过程中岂不是要测试非常多次，似乎有些耗时，这是否有必要呢？是否可以 1 个epoch跑完了之后再进行测试。另外，我使用 RTX 2080 Ti 跑您的 AEN-BERT 模型，batch_size 最大只能设为 16，我看您代码中写的是有16， 32 和 64 三种batch_size，不知道您在论文中的结果是用的多大的 batch_size。

望有空解惑，谢谢！:）

RAM model: RuntimeError: Expected object of scalar type Float but got scalar type Long

When I run

python3 train.py --model_name ram --dataset restaurant --learning_rate 1e-3 --num_epoch 200

I get

RuntimeError: Expected object of scalar type Float but got scalar type Long for sequence element 1 in sequence argument at position #1 'tensors'

aen

what's the learning rate and the num_epochs when tranning AEN-glove MHA model
您好，请问一下AEN-glove MHA训练时候的学习率和迭代次数是多少呢，感觉收敛的特别慢，迭代100次都没达到论文中的0.7178～

10 fold cross validation test results

Hi I ran 10 fold cross validation test as shown in repo60,62, but gain lower results:
twitter：
learning rate 2e-5，mean_test_acc: 0.7095, mean_test_f1: 0.6925
learning rate 5e-5，mean_test_acc: 0.6259, mean_test_f1: 0.5539
restaurant：
learning rate 2e-5，mean_test_acc: 0.7095, mean_test_f1: 0.6925
learning rate 5e-5，mean_test_acc: 0.7407, mean_test_f1: 0.5457

how to solve this problem?

the other parameters are:
parser.add_argument('--model_name', default='aen_bert', type=str)
parser.add_argument('--dataset', default='laptop', type=str, help='twitter, restaurant, laptop')
parser.add_argument('--optimizer', default='adam', type=str)
parser.add_argument('--initializer', default='xavier_uniform_', type=str)
parser.add_argument('--learning_rate', default=2e-5, type=float, help='try 5e-5, 2e-5 for BERT, 1e-3 for others')
parser.add_argument('--dropout', default=0.1, type=float)
parser.add_argument('--l2reg', default=0.01, type=float)
parser.add_argument('--num_epoch', default=10, type=int, help='try larger number for non-BERT models')
parser.add_argument('--batch_size', default=16, type=int, help='try 16, 32, 64 for BERT models')
parser.add_argument('--log_step', default=10, type=int)
parser.add_argument('--embed_dim', default=300, type=int)
parser.add_argument('--hidden_dim', default=300, type=int)
parser.add_argument('--bert_dim', default=768, type=int)
parser.add_argument('--pretrained_bert_name', default='bert-base-uncased', type=str)
parser.add_argument('--max_seq_len', default=80, type=int)
parser.add_argument('--polarities_dim', default=3, type=int)
parser.add_argument('--hops', default=3, type=int)
parser.add_argument('--device', default=None, type=str, help='e.g. cuda:0')
parser.add_argument('--seed', default=None, type=int, help='set seed for reproducibility')
parser.add_argument('--cross_val_fold', default=10, type=int, help='k-fold cross validation')

How to connect glove word embedding and BERT embedding?

If I want to use both of them, how to modify code in aen.py? Thanks a lot.

problem about aen

Hi,

When I try to run aen model, I get the error "can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first." I don't know why and how to fix it. I will be grateful if I can get your reply.

CrossEntropyLoss_LSR is not used?

Hi,

Thanks for the great work.
Just notice that the CrossEntropyLoss_LSR is not referenced at all. So...does that mean I need to manually replace this line?

ABSA-PyTorch/train.py

Line 152 in e4da01e

criterion = nn.CrossEntropyLoss()

BTW, I notice there are some reproducible issues as mentioned in #38. I think it would be great if you could provide the actual commands (random seeds, hyperparameters, etc.) for experiments.

关于实验f1值

您好，请问一下，我直接跑源代码的aen-Bert 发现macro-f1 最高只能到0.68，从没有超过0.7，这个现象在其他的模型中同样存在，请问是我哪里设置有问题，还是说实验跑不到论文中的效果（或者有其他的解释方法？） 谢谢

你好，mgan模块的 第32行 或者那个weight.appen(0)应该把0改成1 ？

因为mgan论文中，本意是要加大aspect词和靠近aspect的那些词的权重？

The accuracy of bert_spc.py is low

I ran the code of bert_spc.py model, the accuracy rate was 65.8%, F1 was 36.5%. Why the accuracy rate was not so high? I used the restaurant data. Was it because of the data set?

Why we use squeeze_embedding

I'm currently somehow confused about why we use squeeze_embedding module to pack the padded sequences and then unpack it ?

Preprocessing Details about SemEval2014 Dataset?

thank you for this nice repo, I have a question: could you share the details of preprocessing on SemEval2014 Dataset (e.g. removing the conflict lable in the dataset ). thanks a lot.

How about significant tests ?

I am confused how to do significant tests with difference metrics, e.g. accuracy and macro-f1.

Request for K-fold cross-validation support

Is it possible to add K-fold cross-validation support to the code?

Import Error

Please look at this
ImportError: /home/linux/anaconda3/envs/absa/lib/python3.7/site-packages/torch/lib/libtorch.so.1: undefined symbol: nvrtcGetProgramLogSize

Another Languages

Thank you so much for your efforts, but I have a question (Do you think that these models could work with datasets in other languages such as Arabic?)

Regards,
Saja

torch.argsort can only be supported in torch.__version__ > 1.0

please mention it in the readme.

Best regard

The CABSAC‘s model have some bugs, I have the loss 0

the .py file don't have run...I want to say, you haven't run it?

训练过程中损失函数的问题

您好，我想请问一下为什么在模型训练过程中损失函数曲线并不是单调递减的趋势，而是抖动下降的状态?起初我觉得是学习率衰减不够，但是修改之后发现并没有用.....

关于aen-bert模型的实验结果复现

作者你好。
在尝试了很多实验之后， aen-bert模型复现遇到了一些瓶颈。
学习率尝试了很多，包括2,3,5e-5等等， epoch也适当增加了多轮次（到了20.30+）

自己的多次实验表明：
res数据集最高只能到82.4的准确率（论文是83.12）
lap数据集最高只能到78.4的准确率（论文是79.93），此结果差别较大

想请问一下是不是我自己操作哪里有问题。
能否麻烦您详细把训练的超参再说明一下。

谢谢。

How can the BERT be applied to aspect-level sentiment analysis?

BERT in your application is to test wheather the sentence B is the actual next sentence that follows sentence A, but what can I do to use the BERT in aspect-level sentiment analysis?