Improving Variational Encoder-Decoders in Dialogue Generation — HN submission

Wed, 11 Apr 2018 20:12:48 GMT

Show HN: Outputs from My Neural Conversational Model

I trained a conversational model on my high-quality dataset. The underlying model is https://arxiv.org/abs/1703.10960 which is open source on Github, with some additional techniques of my own on top of it. I then let it talk with itself for 30 turns for each dialogue. Here are the outputs with some minor post-processing for readability: https://pastebin.com/UsFEFqqh As you can see the results are very diverse and it seems like the model does capture the main topic discussed but fail to compose a natural sentence. It was theorized by [Shen et al](https://arxiv.org/abs/1802.02032) that "BOW…

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Improving Variational Encoder-Decoders in Dialogue Generation · HackerPapers discussions

Improving Variational Encoder-Decoders in Dialogue Generation — HN submission