• Publications
  • Influence
Event Representations for Automated Story Generation with Deep Neural Nets
TLDR
We explore 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. Expand
  • 103
  • 8
  • PDF
Informedia@TrecVID 2014: MED and MER
TLDR
We report on our system used in the TRECVID 2014 Multimedia event Detection (MED) and Multimedia Event Recounting (MER) tasks. Expand
  • 26
  • 3
  • PDF
Identifying Student Leaders from MOOC Discussion Forums through Language Influence
TLDR
We propose an improved method of measuring language accommodation based on people's choice of words given a semantic topic of interest, and show that student leaders indeed coordinate other students’ language usage. Expand
  • 21
  • 2
  • PDF
Controllable Neural Story Plot Generation via Reward Shaping
TLDR
We present a reward-shaping technique 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. Expand
  • 20
  • 1
  • PDF
Story Realization: Expanding Plot Events into Sentences
TLDR
We provide results---including a human subjects study---for a full end-to-end automated story generation system showing that our method generates coherent and plausible stories than baseline approaches. Expand
  • 12
  • 1
  • PDF
Improvisational Computational Storytelling in Open Worlds
TLDR
We propose the grand challenge of creating artificial agents capable of engaging with humans in improvisational, real-time storytelling in open-world domains. Expand
  • 19
  • PDF
Controllable Neural Story Plot Generation via Reinforcement Learning
TLDR
We present a reward-shaping technique 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, resulting in stories that don't have a clear sense of progression and lack coherence. Expand
  • 16
Controllable Neural Story Generation via Reinforcement Learning
TLDR
We introduce a policy gradient reinforcement learning approach to open story generation that learns to achieve a given narrative goal state. Expand
  • 7
  • PDF
Guided Neural Language Generation for Automated Storytelling
TLDR
Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Expand
  • 8
  • PDF
Utterance classification in speech-to-speech translation for zero-resource languages in the hospital administration domain
TLDR
We are developing a language-independent dialogue system which can easily support new languages without any linguistic knowledge or expertise of the user. Expand
  • 7
  • PDF