search

JiyaoWei / bilstm_mpoa

Sentiment analysis has been a popular field in natural language processing. Sentiments can be expressed explicitly or implicitly. Most current studies on sentiment analysis focus on the identification of explicit sentiments. However, implicit sentiment analysis has become one of the most difficult tasks in sentiment analysis due to the absence of explicit sentiment words. In this article, we propose a BiLSTM model with multi-polarity orthogonal attention for implicit sentiment analysis. Compared to the traditional single attention model, the difference between the words and the sentiment orientation can be identified by using multi-polarity attention. This difference can be regarded as a significant feature for implicit sen timent analysis. Moreover, an orthogonal restriction mechanism is adopted to ensure that the discrim inatory performance can be maintained during optimization. The experimental results on the SMP2019 implicit sentiment analysis dataset and two explicit sentiment analysis datasets demonstrate that our model more accurately captures the characteristic differences among sentiment polarities.
14 stars 1 forks source link

about vocab #3

Open StudentWorker opened 2 years ago

StudentWorker commented 2 years ago

Do I divide sentences into word or words？ Whether the process is a word - > de stop word - > use wordtovect - > create dictionary. I have to run out. and already learn some vocab，RNN，or lstm

StudentWorker commented 2 years ago

I want to write a file to generate vocab, and then upload it to later people. To deepen the understanding of vocab.

JiyaoWei commented 2 years ago

Sentences are divided into words, because the emotion dictionary we used is made up of words.

StudentWorker commented 2 years ago

My understanding is that as long as I filter some words according to word frequency.

Provide a similar

理解 开心 不能

that will do. I don't know my understanding, right Thank you for your reply

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2021年11月12日(星期五) 下午3:26 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

Sentences are divided into words, because the emotion dictionary we used is made up of words.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

StudentWorker commented 2 years ago

How should I handle these files to match the code

SMP2019 ECISA Dev.xml

SMP2019 ECISA Test.xml

SMP2019 ECISA Train.xml

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2021年11月12日(星期五) 下午3:26 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

Sentences are divided into words, because the emotion dictionary we used is made up of words.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

StudentWorker commented 2 years ago

I think I've solved most of the preprocessing. I want to ask, Elmo_path Where should I find the 

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2021年11月12日(星期五) 下午3:26 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

Sentences are divided into words, because the emotion dictionary we used is made up of words.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

JiyaoWei commented 2 years ago

Elmo_path is similar to vocab_path, you need to general it from the experiment dataset. You can refer to https://github.com/HIT-SCIR/ELMoForManyLangs. Of course, elmo is not essential.

StudentWorker commented 2 years ago

this

get query matrix

h5py.File(args.elmo_path, 'r')

emo_ vector = json.load(f)

I think I should have finished all but these two documents. I want to know if my form of Dalian University of technology is to become JSON? And this Elmo, I have a simplified Chinese version, but it doesn't correspond to it. How to correspond to this h5py

StudentWorker commented 2 years ago

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!)

想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional)

并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

StudentWorker commented 2 years ago

query_embedding  the last question what is this?how can i got it .

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2021年11月16日(星期二) 晚上9:51 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

Elmo_path is similar to vocab_path, you need to general it from the experiment dataset. You can refer to https://github.com/HIT-SCIR/ELMoForManyLangs. Of course, elmo is not essential.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

JiyaoWei commented 2 years ago

emo_ vector是情感词向量，我们是通过对大连理工情感词点中的不同情感极性词汇的向量表示求平均得到的，在论文中是有说明的

StudentWorker commented 2 years ago

我已经解决该问题，并已经跑起来了，谢谢。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:18 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

emo_ vector是情感词向量，我们是通过对大连理工情感词点中的不同情感极性词汇的向量表示求平均得到的，在论文中是有说明的

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

StudentWorker commented 2 years ago

不过我想问一问，这个平均值的区间是？ -无穷到0 消极情绪    0到正无穷 积极情绪   那么中性词性的是？

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:18 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

emo_ vector是情感词向量，我们是通过对大连理工情感词点中的不同情感极性词汇的向量表示求平均得到的，在论文中是有说明的

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

JiyaoWei commented 2 years ago

情感词表可以参考http://ir.dlut.edu.cn/info/1013/1142.htm，每种情感都有一个词汇集合，是有中性词集合的

StudentWorker commented 2 years ago

遗憾的是，我无法登录该网站。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:40 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

情感词表可以参考http://ir.dlut.edu.cn/info/1013/1142.htm，每种情感都有一个词汇集合，是有中性词集合的

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

JiyaoWei commented 2 years ago
image

http://ir.dlut.edu.cn/info/1013/1142.htm

JiyaoWei commented 2 years ago

他们网址不久前更新了，抱歉哈

StudentWorker commented 2 years ago

好的，谢谢。我虽然跑起来了，但是用的是极左极右两个方面的作为平均值。当时我在考虑，你是不是用的 - 到-.3 -0.3到0.3  0.3到+ 因为我用的是英文情感词典。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:44 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

http://ir.dlut.edu.cn/info/1013/1142.htm — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

JiyaoWei commented 2 years ago

这样平均划分的思想相同，也是没有问题的～

StudentWorker commented 2 years ago

其实这个平均划分的思想，我在想，是不是要基于数据集是平均划分，我觉得基于词典去平均划分，是不是有一定的理想成分，毕竟每个数据集的平均值可能是不一样的。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:51 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

这样平均划分的思想相同，也是没有问题的～

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

StudentWorker commented 2 years ago

是否有必要搞一个端到端的平均值求解。根据数据集，求出平均值。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:51 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

这样平均划分的思想相同，也是没有问题的～

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

JiyaoWei commented 2 years ago

确实有这样的问题存在，每个数据集的标注者不一样，可能会存在偏见，是一个值得探索的问题

JiyaoWei commented 2 years ago

可以尝试一下👍

StudentWorker commented 1 year ago

当然这只是我引用了你论文的一点小建议，如果你还在学术的路径奔跑，其实是可以思考数据集到平均值这一步的，而且最新的tranformer的词向量也差很多。我已经就情感分析做了一些努力，现在打算转图像了。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年4月24日(星期天) 下午4:57 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

确实有这样的问题存在，每个数据集的标注者不一样，可能会存在偏见，是一个值得探索的问题

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

cjj-sunshine commented 1 year ago

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！ error

StudentWorker commented 1 year ago

形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月18日(星期五) 晚上9:05 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

cjj-sunshine commented 1 year ago

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上9:08 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。

------------------ 原始邮件 ------------------ 发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:05 收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

StudentWorker commented 1 year ago

pycharm 选择错误点直接把形参类型改掉，就是这堆。 (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!)  把它改成对应匹配的类型。Python对元组的约束，本身就很不严谨。所以list和tuple不那么重要。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月18日(星期五) 晚上9:53 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上9:08 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。

------------------ 原始邮件 ------------------
发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:05
收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

cjj-sunshine commented 1 year ago

好的，谢谢！

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上10:17 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

pycharm 选择错误点直接把形参类型改掉，就是这堆。 (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!)  把它改成对应匹配的类型。Python对元组的约束，本身就很不严谨。所以list和tuple不那么重要。

------------------ 原始邮件 ------------------ 发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:53 收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？

------------------ 原始邮件 ------------------
发件人: "JiyaoWei/bilstm_mpoa" @.>;
发送时间: 2022年11月18日(星期五) 晚上9:08
@.>;
@.**@.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。

------------------ 原始邮件 ------------------
发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:05
收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.>
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

StudentWorker commented 1 year ago

需要修改rnn.py

        else:             # result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,             #                   self.num_layers, self.dropout, self.training, self.bidirectional)

            result = _VF.lstm(input, batch_sizes, tuple(hx),tuple(self._flat_weights), self.bias,                               self.num_layers, self.dropout, self.training, bool(self.bidirectional))

给你提供我做好的笔记。修改rnn类库下的文件，即可执行代码。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月18日(星期五) 晚上10:22 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

好的，谢谢！

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上10:17 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

pycharm 选择错误点直接把形参类型改掉，就是这堆。 (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!)  把它改成对应匹配的类型。Python对元组的约束，本身就很不严谨。所以list和tuple不那么重要。

------------------ 原始邮件 ------------------
发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:53
收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？

------------------ 原始邮件 ------------------
发件人: "JiyaoWei/bilstm_mpoa" @.>;
发送时间: 2022年11月18日(星期五) 晚上9:08
@.>;
@.**@.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 

形参不匹配，我当时修改了类库。就是直接把这个 * (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)  * (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。    

------------------ 原始邮件 ------------------    
发件人: ***@***.***>;     
发送时间: 2022年11月18日(星期五) 晚上9:05    
收件人: ***@***.***>;     
抄送: ***@***.***>; ***@***.***>;     
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)    

选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:  * (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)  * (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。    

您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！    

—    
Reply to this email directly, view it on GitHub, or unsubscribe.    
You are receiving this because you authored the thread.Message ID: ***@***.***>

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.>
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>

cjj-sunshine commented 1 year ago

可以运行了，感谢大佬！！！

------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上10:23 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

需要修改rnn.py

        else:             # result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,             #                   self.num_layers, self.dropout, self.training, self.bidirectional)

            result = _VF.lstm(input, batch_sizes, tuple(hx),tuple(self._flat_weights), self.bias,                               self.num_layers, self.dropout, self.training, bool(self.bidirectional))

给你提供我做好的笔记。修改rnn类库下的文件，即可执行代码。

------------------ 原始邮件 ------------------ 发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上10:22 收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

好的，谢谢！

------------------ 原始邮件 ------------------
发件人: "JiyaoWei/bilstm_mpoa" @.>;
发送时间: 2022年11月18日(星期五) 晚上10:17
@.>;
@.**@.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

pycharm 选择错误点直接把形参类型改掉，就是这堆。 (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!)  把它改成对应匹配的类型。Python对元组的约束，本身就很不严谨。所以list和tuple不那么重要。

------------------ 原始邮件 ------------------
发件人: @.>;
发送时间: 2022年11月18日(星期五) 晚上9:53
收件人: @.>;
抄送: @.>; @.>;
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？    

------------------ 原始邮件 ------------------    
发件人:                                                                                                                        "JiyaoWei/bilstm_mpoa"                                                                                    ***@***.***>;    
发送时间: 2022年11月18日(星期五) 晚上9:08    
***@***.***>;    
***@***.******@***.***>;    
主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)    

 形参不匹配，我当时修改了类库。就是直接把这个 * (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)  * (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。     

 ------------------ 原始邮件 ------------------     
 发件人: ***@***.***>;      
 发送时间: 2022年11月18日(星期五) 晚上9:05     
 收件人: ***@***.***>;      
 抄送: ***@***.***>; ***@***.***>;      
 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)     

 选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:  * (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)  * (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。     

 您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！     

 —     
 Reply to this email directly, view it on GitHub, or unsubscribe.     
 You are receiving this because you authored the thread.Message ID: ***@***.***>     
—    
Reply to this email directly, view it on GitHub, or unsubscribe.    
You are receiving this because you commented.Message ID: ***@***.***>

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.>
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.>
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

gm199956 commented 1 year ago

你好，数据集的网站打不开，能提供一个别的链接（比如百度网盘链接）吗。拿到数据后，需要用jieba分词把所有句子的词汇汇总为一个词汇表吗？谢谢。

StudentWorker commented 1 year ago

我不是作者，有关数据的问题，无法回答。一年前做的了，忘了。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月23日(星期三) 上午10:24 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

你好，数据集的网站打不开，能提供一个别的链接（比如百度网盘链接）吗。拿到数据后，需要用jieba分词把所有句子的词汇汇总为一个词汇表吗？谢谢。

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

gm199956 commented 1 year ago

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？ ... ------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上9:08 @.>; @.**@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。 ------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月18日(星期五) 晚上9:05 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。 您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

大佬，方便加个好友或留个邮件，请教您一下代码复现的问题吗？万分感谢！

StudentWorker commented 1 year ago

你应该问一下那个可以运行的哥们，我教他了。我手头已经没有相关的代码和结构了。

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月28日(星期一) 晚上7:21 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3)

非常感谢您的回复，但是我没有找到这个类库在哪个地方，还有您是怎么修改的，方便细说一下吗？ ... ------------------ 原始邮件 ------------------ 发件人: "JiyaoWei/bilstm_mpoa" @.>; 发送时间: 2022年11月18日(星期五) 晚上9:08 @.>; @.@.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 形参不匹配，我当时修改了类库。就是直接把这个  (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights,库的源代码改掉了。 ------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月18日(星期五) 晚上9:05 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [JiyaoWei/bilstm_mpoa] about vocab (Issue #3) 选择mopa的时候，执行结果是。 TypeError: lstm() received an invalid combination of arguments - got (Tensor, Tensor, tuple, list, bool, int, float, bool, int), but expected one of:   (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)       didn't match because some of the arguments have invalid types: (Tensor, Tensor, !tuple!, !list!, bool, int, float, bool, !int!)   (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)       didn't match because some of the arguments have invalid types: (Tensor, !Tensor!, !tuple!, !list!, !bool!, int, !float!, bool, !int!) 想知道 result = _VF.lstm(input, batch_sizes, hx, self._flat_weights, self.bias,                   self.num_layers, self.dropout, self.training, self.bidirectional) 并没有提示我正确的应该是，也无法进入方法，我想知道，难道hx不是tuple么，_flat_weights不是list么，还有self.bidirectional不是Int么。 您好，我也遇到了同样的问题，请问是怎么解决的，希望能尽快得到您的回复！ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.>

大佬，方便加个好友或留个邮件，请教您一下代码复现的问题吗？万分感谢！

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>