Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This addresses a key limitation in neural dialog systems for improving human-computer interaction, though it is incremental as it builds on existing translation methods.
The paper investigates why neural dialog systems produce short and meaningless replies, conjecturing that multiple plausible replies cause neural network deficiencies, and reproduces this phenomenon in machine translation to provide evidence.
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equally plausible replies, causing the deficiency of neural networks in the dialog application. We propose a systematic way to mimic the dialog scenario in a machine translation system, and manage to reproduce the phenomenon of generating short and less meaningful sentences in the translation setting, showing evidence of our conjecture.