This post is about my own paper to appear at ACL later this month. What is interesting about this paper will depend on your research interests, so that’s how I’ve broken down this blog post.
A few key points first:
Data and code are available on Github. The paper is also available. The general-purpose span labeling and linking annotation tool we used is also appearing at ACL. Check out DSTC 8 Track 2, which is based on this work.
For a more flexible dialogue system, use the crowd to propose and vote on responses, then introduce agents and a model for voting, gradually learning to replace the crowd.
A new dialogue dataset that has annotations of multiple plans (frames) and dialogue acts that indicate modifications to them.
During task-oriented dialogue generation, to take into consideration a table of information about entities, represent it as a graph, run message passing to get vector representations of each entity, and use attention.
Identifying the key phrases in a dialogue at the same time as identifying the type of relations between pairs of utterances leads to substantial improvements on both tasks.