Melissa Roemmele
Scholar

Melissa Roemmele

Google Scholar ID: l_nZmdkAAAAJ
Midjourney
natural language processingnatural language generationcomputational creativityhuman-computer
Citations & Impact
All-time
Citations
1,330
 
H-index
12
 
i10-index
13
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Projects: Narrative Visualization, AI-Augmented Creative Writing, Evaluation Benchmarks for LLMs; Published multiple academic papers such as 'LLMs Behind the Scenes: Enabling Narrative Scene Illustration' and 'Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing'.
Research Experience
  • Worked in the Language Weaver division at RWS (formerly SDL) on a range of NLP tasks including summarization and machine translation quality estimation; Research Assistant in the Narrative Group led by Andrew Gordon at the USC Institute for Creative Technologies.
Education
  • PhD in Computer Science from the University of Southern California, advised by Andrew Gordon, dissertation explored emerging applications of language modeling to interactive story generation; Master's degree in Computational Linguistics from Indiana University; Bachelor's degree in Psychology and Linguistics from Miami University.
Background
  • Research Interests: Natural Language Processing (NLP) and Human-Computer Interaction (HCI), using AI to augment human creativity. Currently part of the Midjourney Storytelling Lab, developing AI-based tools to facilitate novel ways to tell stories. Focuses on evaluating and optimizing natural language interfaces for these tools, especially with regard to prompting techniques for large language models (LLMs) and text-to-image models.
Miscellany
  • Was part of the Diving team during undergraduate studies.