Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
Not on the map. Why?
Abstract (arXiv)
Although people have the ability to engage in vapid dialogue without effort, this may not be a uniquely human trait. Since the 1960's researchers have been trying to create agents that can generate artificial conversation. These programs are commonly known as chatbots. With increasing use of neural networks for dialog generation, some conclude that this goal has been achieved. This research joins the quest by creating a dialog generating Recurrent Neural Network (RNN) and by enhancing the ability of this network with auxiliary loss functions and a beam search. Our custom loss functions achieve better cohesion and coherence by including calculations of Maximum Mutual Information (MMI) and entropy. We demonstrate the effectiveness of this system by using a set of custom evaluation metrics inspired by an abundance of previous research and based on tried-and-true principles of Natural Language Processing.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 11 of its 31 references that are in the map. First posted on arXiv 4 Jun 2021.
Builds on
11 of 31 references.
References · 11
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
- 2016How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generationcited by 356
- 2016Deep Reinforcement Learning for Dialogue Generationcited by 286
- 2015A Neural Conversational Modelcited by 195
- 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
- 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
- 2018Learning Longer-term Dependencies in RNNs with Auxiliary Lossescited by 58
- 2017Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Modelscited by 42
- 2018Natural Language Generation by Hierarchical Decoding with Linguistic Patternscited by 11
Built on by
Citing papers per year: 2023: 1.
1 paper.