Lara J. Martin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lara J. Martin has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Ethan Tien
Georgia Institute of Technology
1 shared publication - Mark Owen Riedl
Georgia Institute of Technology
1 shared publication - Prithviraj Ammanabrolu
Facebook AI Research Georgia Institute of Technology
1 shared publication - Wesley Cheung
School of Interactive Computing Georgia Institute of Technology
1 shared publication William Ma
School of Interactive Computing Georgia Institute of Technology
1 shared publication- Zhaochen Luo
Georgia Institute of Technology
1 shared publication
Latest Publications
- Open Access
Story Realization: Expanding Plot Events into Sentences
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. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events.We provide results---including a human subjects study---for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches.
Open AccessStory Realization: Expanding Plot Events into Sentences
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. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events.We provide results---including a human subjects study---for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches.