255 citations · 1.3k across the 24 of their papers we have counts for
3 papers · 1 filter
A Diversity-Promoting Objective Function for Neural Conversation Models
Jiwei Li, Michel Galley, Chris Brockett +2
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. W…
deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
Michel Galley, Chris Brockett, Alessandro Sordoni +6
We introduce Discriminative BLEU (deltaBLEU), a novel metric for intrinsic evaluation of generated text in tasks that admit a diverse range of possible outputs. Reference strings a…
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
Alessandro Sordoni, Michel Galley, Michael Auli +6
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to add…