DIALogue-level Commonsense Transformer (DIALeCT)

本文介绍了DIALeCT（对话级通识常识转换器）的预训练检查点。

该模型基于 T5-large 检查点进行训练。

数据集

可以按照以下说明获取用于预训练模型的数据集。上下文化对话通识推理（CICEROv2）包括标注的通识推理，包括原因和情感反应等。对话来自多个数据集。

示例

以下是通过预训练模型生成的一些结果示例（零-shot设置）。

随后的事件

What is or could be the subsequent event of the target? <sep> 
target: Oh . I just can't forget it .<sep> 
context: A: David , why didn't you clean the room ?, <utt> 
B: I'm not in the mood ., <utt> 
A: Why are you feeling depressed ?, <utt> 
B: I was told my girlfriend was speaking ill of me. That \u2019 s a real let-down ., <utt> 
A: I don t think she will do such a thing ., <utt> 
B: But she did and made me disappointed ., <utt> 
A: Oh , cheer up . A girlfriend is not everything ., <utt> 
B: But she means a lot to me ., <utt> 
A: Then forgive her mistake ., <utt> 
B: Oh . I just can't forget it 

预测的随后事件：

David's girlfriend apologized to david for her mistake.

原因

What is or could be the cause of target? <sep> 
target: Thanks. Will I be able to take a retest ? <sep> 
context: A: Did I do well on my test ?, <utt> 
B: Do you want to know the honest answer ?, <utt> 
A: Why wouldn't I want to know ?, <utt> 
B: You had pretty bad scores ., <utt> 
A: Exactly what do you mean by bad ?, <utt> 
B: You failed ., <utt> 
A: How'd I fail it ?, <utt> 
B: There are a couple of reasons why you didn't pass ., <utt> 
A: What did I do wrong ?, <utt> 
B: To sum it all up , you really just don't know how to drive ., <utt> 
A: Thanks. Will I be able to take a retest ?, <utt> 
B: Sure you can , in about two and a half weeks . 

预测的原因：

The speaker has failed the driving test.

情感反应

What is the possible emotional reaction of the listener in response to target? <sep> 
target: Oh . I just can't forget it .<sep> 
context: A: David , why didn't you clean the room ?, <utt> 
B: I'm not in the mood ., <utt> 
A: Why are you feeling depressed ?, <utt>
B: I was told my girlfriend was speaking ill of me. That \u2019 s a real let-down ., <utt> 
A: I don t think she will do such a thing ., <utt> 
B: But she did and made me disappointed ., <utt> 
A: Oh , cheer up . A girlfriend is not everything ., <utt> 
B: But she means a lot to me ., <utt> 
A: Then forgive her mistake ., <utt> 
B: Oh . I just can't forget it 

预测的情感反应：

The listener is hopeful that david will forgive his girlfriend for her mistake.

推理：

输入文本应按以下格式进行格式化。

Question <sep> target: target_utt <sep> context: A: utterance 1 <utt> B: utterance 2 <utt> A: utterance 3 <utt> B: utterance 4

问题：我们想要进行推理的问题。

A，B是讲话者标识符

target_utt可以是utterance 1，utterance 2，utterance 3或utterance 4之间的任何一个。在target_utt中不要使用讲话者标识符。

Hosted inference API示例中提供了一些样本。

BibTeX参考文献和引用信息

如果您使用该模型，请引用：

@article{Shen2022MultiviewCC,
  title={Multiview Contextual Commonsense Inference: A New Dataset and Task},
  author={Siqi Shen and Deepanway Ghosal and Navonil Majumder and Henry Lim and Rada Mihalcea and Soujanya Poria},
  journal={ArXiv},
  year={2022},
  volume={abs/2210.02890}
}