462 citations · 2.2k across the 15 of their papers we have counts for
4 papers · 2 filters
A Simple, Fast Diverse Decoding Algorithm for Neural Generation
Jiwei Li, Will Monroe, Dan Jurafsky
In this paper, we propose a simple, fast decoding algorithm that fosters diversity in neural generation. The algorithm modifies the standard beam search algorithm by adding an inte…
Neural Net Models for Open-Domain Discourse Coherence
Jiwei Li, Dan Jurafsky
Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. Yet existing models of coherence focus on measur…
Deep Reinforcement Learning for Dialogue Generation
Jiwei Li, Will Monroe, Alan Ritter +3
Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time…
Mutual Information and Diverse Decoding Improve Neural Machine Translation
Jiwei Li, Dan Jurafsky
Sequence-to-sequence neural translation models learn semantic and syntactic relations between sentence pairs by optimizing the likelihood of the target given the source, i.e., $p(y…