Turn-Taking Predictions across Languages and Genres Using an LSTM Recurrent Neural Network
Turn-Taking Predictions across Languages and Genres Using an LSTM Recurrent Neural Network
复制标题
使用 LSTM 递归神经网络进行跨语言和流派的轮流预测
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
O. Fuentes
中科院分区：
文献类型：
--
作者：
Nigel G. Ward;Diego Aguirre;Gerardo Cervantes;O. Fuentes
除了为解决特定任务而构建的轮流模型（例如预测用户在暂停后是否会保持轮流）之外，人们对包含许多此类任务的更通用的轮流模型越来越感兴趣，并且最近已经获得了非常好的结果[1]。在这里，我们提出了一种改进的循环网络模型，其性能优于[1]，并且无需词汇注释即可实现。此外，我们表明该模型可以在不进行修改的情况下针对不同语言进行训练，在英语、西班牙语、日语、普通话和法语的轮流预测中提供良好的结果。我们还表明，我们的模型在各种类型上都表现良好，包括面向任务的对话和一般对话。
Going beyond turn-taking models built to solve specific tasks, such as predicting if a user will hold his/her turn after a pause, there is growing interest in more general models for turn taking that subsume many such tasks, and very good results have recently been obtained [1]. Here we present an improved recurrent network model that outperforms [1] and does so without requiring lexical annotation. Further, we show that this model can be trained for different languages with no modifications, providing good results in turn-taking prediction for English, Spanish, Japanese, Mandarin and French. We also show that our model performs well across genres, including task-oriented dialog and general conversation.