动机
一个好的对话需要保持平衡:简洁与细节 持续主题与更换主题 问问题和回答问题
对应四种属性:重复性、独特性、回复相关性和问与答
lowlevel model attributes—Conditional Training
•控制加入句子表示的特征
•将输入x与属性概率z作为解码器的输入生成y
lowlevel model attributes—weighted decoding
•在测试时将特征加入目标函数
•这个特征只能是词的特征
Controlling conversational attributes——重复——weighted decoding
•分三种:对话中的自我重复、非对话中的自我重复、重复对方的话(赋予负的权重)
Controlling conversational attributes——独特
R是所有响应个数,cw是是包含词w的响应个数,然后将它标准化
Controlling conversational attributes——回复相关
•weighted decoding
•the cosine similarity between the GloVe embedding for the word w, and the sentence embedding for the partner’s last utterance ‘
•conditional training
the overall cosine similarity between the partner’s last utterance ‘ and the model’s response y 发现没有效果
Controlling conversational attributes——问与答的平衡
•weighted decoding
•是否有问词
•副作用:负权重影响这种句子的生成I’m learning how to knit
•正权重:正权重容易生成What??????? or Who? When? How?)这种句子
•conditional training,
•与以往工作中在句子层面进行控制不同,本文在对话层面进行控制,比如e.g.20% questions or 70% questions
We train our CT modelon a control variable z with 11 possible values:
(1……10)i/10是概率
结果:
conditional training方式更好
疑问词:how, what, when, where, which, who, whom,whose,why
另建立了一个交流群,感兴趣的朋友可以加下
更多推荐
《What makes a good conversation?How controllable attributes affect human judgmen
发布评论