• Publications
  • Influence
Event Representations for Automated Story Generation with Deep Neural Nets
TLDR
The question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity is explored.
Story Realization: Expanding Plot Events into Sentences
TLDR
An ensemble-based model that generates natural language guided by events is presented that generates more coherent and plausible stories than baseline approaches 1.
Informedia@TrecVID 2014: MED and MER
TLDR
On the MED task, the CMU team achieved leading performance in the Semantic Query, 000Ex, 010Ex and 100Ex settings, and the system utilizes a subset of features and detection results from the MED system from which the recounting is then generated.
Controllable Neural Story Plot Generation via Reward Shaping
TLDR
A reward-shaping technique is presented that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal.
Identifying Student Leaders from MOOC Discussion Forums through Language Influence
TLDR
An improved method of measuring language accommodation based on people’s choice of words given a semantic topic of interest is proposed, and it is shown that student leaders indeed coordinate other students’ language usage.
Guided Neural Language Generation for Automated Storytelling
TLDR
This work presents an ensemble-based model that generates natural language guided by events that outperforms the baseline sequence-to-sequence model and provides results for a full end- to-end automated story generation system.
Controllable Neural Story Plot Generation via Reinforcement Learning
TLDR
A reward-shaping technique is presented that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal.
Improvisational Computational Storytelling in Open Worlds
TLDR
This work proposes the grand challenge of computational improvisational storytelling in open-world domains and lays out some of the research challenges and proposes two agent architectures that can provide the basis for exploring the research issues surrounding open- world human-agent interactions.
Controllable Neural Story Generation via Reinforcement Learning
TLDR
A human subject evaluation shows that stories generated by the introduced policy gradient reinforcement learning approach to open story generation are perceived to have significantly higher plausible event ordering and plot coherence over a baseline language modeling technique without perceived degradation of overall quality, enjoyability, or local causality.
Dungeons and DQNs: Toward Reinforcement Learning Agents that Play Tabletop Roleplaying Games
TLDR
This paper presents an approach for reinforcement learning agents that can play tabletop roleplaying games as a challenge due to an infinite action space, multiple (collaborative) players and models of the world, and no explicit reward signal.
...
1
2
...