A Diversity-Promoting Objective Function for Neural Conversation Models — mentioned by Imnimo

Fri, 10 Jun 2022 16:33:51 GMT

It wasn't so long ago that researchers were worried their chatbots said "I don't know" too much: https://arxiv.org/pdf/1510.03055.pdf >Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don’t know) regardless of the input. We suggest that the traditional objective function, i.e., the likelihood of output (response) given input (message) is unsuited to response generation tasks. And now we find that these giant models don't even know when to say that they don't know! Of course, the old models weren't…

Paper and discussion history. A mention is not an endorsement.

A Diversity-Promoting Objective Function for Neural Conversation Models — mentioned by ram21

Tue, 24 Nov 2015 00:17:26 GMT

Thank you. You mentioned that you plan on adding a re-ranker. Is that a re-ranker that encourages diversity? Just like what is done in this paper: http://arxiv.org/pdf/1510.03055.pdf

Paper and discussion history. A mention is not an endorsement.

A Diversity-Promoting Objective Function for Neural Conversation Models · HackerPapers discussions

A Diversity-Promoting Objective Function for Neural Conversation Models — mentioned by Imnimo

A Diversity-Promoting Objective Function for Neural Conversation Models — mentioned by ram21