Investigating Deep Learning for Predicting Multi-linguistic Interactions with a Chatterbot
Investigating Deep Learning for Predicting Multi-linguistic Interactions with a Chatterbot
复制标题
研究深度学习以预测与聊天机器人的多语言交互
DOI：
10.1109/icbda50157.2020.9289710
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Patricia Morreale
中科院分区：
文献类型：
--
作者：
R. Kulesza;Y. Kumar;R. Ruiz;A. Torres;E. Weinman;J. J. Li;Patricia Morreale
深度学习因其在图像识别、语音翻译、语言预测和翻译等方面的成功应用而成为人工智能机器学习的主流技术。我们正在研究DL神经网络(NN)的基本原理，以设计最优的DL神经网络来预测人类与Chatterbot的多语言对话。这项研究试图解决为不同特征的数据寻找最优神经网络设计这一众所周知的开放问题。我们特别关注具有时间进度的递归神经网络(RNN)模型，该模型考虑了前一步的结果加上当前输入来预测下一步，即它‘记住’它以前学到的东西。通过对RNN进行优化，使其在准确率和训练时间上达到最优，我们发现字数和神经元层数等特征都会影响训练性能。我们将优化后的最优模型应用到一个游戏实现中，灵感来自IBM Watson，用户可以猜测要由计算机生成的单词，该计算机名为“Beats AI”，让人类预测机器的预测。
Deep Learning (DL) becomes a mainstream technique for Artificial Intelligence (AI) machine learning because of its success in performing many tasks, such as image recognition, speech interpretation, language prediction and translation. We are investigating the underlying principles of DL Neural Networks (NN) to design optimal DL NN for predicting human multi-linguistic conversations with a chatterbot. This research attempts to tackle the well-known open problem of finding optimal NN designs for data of various characteristics. We are in particular focusing on Recurrent Neural Networks (RNN) models with time progression, which takes into consideration the results from the previous steps plus the current input to predict the next step, i.e. it ‘remembers’ what it has previously learnt. Through the experiments of tuning an RNN to achieve an optimal performance in terms of accuracy and training time, we found that characteristics such as word counts and layers of neurons could affect the training performance. We applied the tuned optimal model to a game implementation, inspired by IBM Watson, where users can guess the words to be generated by a computer, called “Beat AI” to have human predict the machine prediction.