• Publications
  • Influence
Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation
TLDR
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and asequence of natural language tokens. Expand
  • 155
  • 24
  • PDF
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
TLDR
We present the results of applying our techniques on text, graph, and text-to-graph based models, and discuss implications for the use of external knowledge in solving the NLI problem. Expand
  • 40
  • 6
  • PDF
Evaluating Temporal Planning Domains
TLDR
The last eight years have seen dramatic progress in temporal planning as highlighted by the temporal track in the last three International Planning Competitions (IPC). Expand
  • 36
  • 6
  • PDF
Dude, srsly?: The Surprisingly Formal Nature of Twitter's Language
TLDR
Twitter has become the de facto information sharing and communication platform. Expand
  • 82
  • 5
  • PDF
Integrating a Closed World Planner with an Open World Robot: A Case Study
TLDR
In this paper, we present an integrated planning and robotic architecture that actively directs an agent engaged in an urban search and rescue (USAR) scenario. Expand
  • 46
  • 4
  • PDF
Coordination in human-robot teams using mental modeling and plan recognition
TLDR
In this paper, we cast the evolving and complex structure of beliefs, and inference over them, as a planning and plan recognition problem. Expand
  • 66
  • 3
  • PDF
Predicting User Engagement on Twitter with Real-World Events
TLDR
We operationalize a person’s Twitter engagement with a real-world event as the posting of tweets about that event, including retweets and replies related to the event (e.g. posting or exchanging event-related tweets). Expand
  • 28
  • 2
  • PDF
Tell me when and why to do it! Run-time planner model updates via natural language instruction
TLDR
Robots are currently being used in and developed for critical HRI applications such as search and rescue. Expand
  • 74
  • 1
  • PDF
Planning for human-robot teaming in open worlds
TLDR
In this article, we focus on adapting planning technology to Urban Search And Rescue (USAR) with a human-robot team with open world quantified goals. Expand
  • 80
  • 1
  • PDF
Planning for serendipity
TLDR
We formalize this notion of planning for serendipity for the first time, and provide an Integer Programming based solution for this problem. Expand
  • 35
  • 1
  • PDF
...
1
2
3
4
5
...