Melissa Roemmele

melissa @ roemmele.io | CV/Resume | LinkedIn | GitHub

I'm a Research Scientist on the Storytelling team at Midjourney. My particular research passion involves the use of computers to analyze and augment human creativity in language and storytelling. More broadly, I'm interested in using AI to expand the possibilities of language-based interaction between people and machines.

In 2018, I received my PhD in the Department of Computer Science at University of Southern California. My thesis "Neural Networks for Narrative Continuation" explored machine learning approaches to automatically predicting 'what happens next' in text-based stories (see the one-page abstract or the full text). As a PhD student, I worked as a research assistant in the Narrative Group led by my advisor Andrew Gordon at the USC Institute for Creative Technologies. Before coming to USC, I completed a Master's degree in Computational Linguistics at Indiana University. As an undergraduate I studied Psychology and Linguistics at Miami University, where I was also part of the Diving team.

Media

  • ACM Chicago talk about AI-augmented creative writing. video | slides
  • ACM Article: "Engineering Additional Creativity". html

Publications (also on Google Scholar).

  • Melissa Roemmele and Andrew Gordon (2024). From Test-Taking to Test-Making: LLM Authoring of Evaluation Benchmarks. Findings of the Association for Computational Linguistics: EMNLP 2024. pdf
  • John Joon Young Chung, Melissa Roemmele, and Max Kreminski (2024). Toyteller: Toy-Playing with Character Symbols for AI-Powered Visual Storytelling. 37th Annual ACM Symposium on User Interface Software and Technology (UIST '24). pdf
  • Melissa Roemmele, Kyle Shaffer, Katrina Olsen, Yiyi Wang, and Steve DeNeefe (2023). AbLit: A Resource for Analyzing and Generating Abridged Versions of English Literature. 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023). pdf
  • Melissa Roemmele (2021). Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing. 12th International Conference on Computational Creativity (ICCC 2021). pdf | video | slides | summary
  • Melissa Roemmele, Deep Sidhpura, Steve DeNeefe, and Ling Tsou (2021). AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents. 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), Demo Track. pdf | poster | article
  • Melissa Roemmele (2019). Identifying Sensible Lexical Relations in Generated Stories. Workshop on Narrative Understanding at the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2019). pdf
  • Melissa Roemmele and Andrew Gordon (2018). Linguistic Features of Helpfulness in Automated Support for Creative Writing. Storytelling Workshop at the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2018). pdf
  • Melissa Roemmele and Andrew Gordon (2018). An Encoder-decoder Approach to Predicting Causal Relations in Stories. Storytelling Workshop at the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2018). pdf
  • Melissa Roemmele (2018). Neural Networks for Narrative Continuation. PhD Thesis. University of Southern California. pdf
  • Melissa Roemmele and Andrew Gordon (2018). Automated Assistance for Creative Writing with an RNN Language Model. Demo at the 2018 International Conference on Intelligent User Interfaces (IUI 2018). pdf | demo
  • Melissa Roemmele and Andrew Gordon (2017). Lexical preferences in an automated story writing system. Workshop on Machine Learning for Creativity and Design, at the Thirty-First Annual Conference on Neural Information Processing Systems (NIPS 2017). pdf
  • Margaret Cychosz, Andrew Gordon, Obiageli Odimegwu, Olivia Connolly, Jenna Bellassai, and Melissa Roemmele (2017). Effective Scenario Designs for Free-text Interactive Fiction. 10th International Conference on Interactive Digital Storytelling (ICIDS-2017). pdf
  • Jenna Bellassai, Andrew Gordon, Melissa Roemmele, Margaret Cychosz, Obiageli Odimegwu, and Olivia Connolly (2017). Unsupervised Text Classification for Natural Language Interactive Narratives. Proceedings of the 10th International Workshop on Intelligent Narrative Technologies (INT10). pdf
  • Melissa Roemmele, Andrew Gordon, and Reid Swanson (2017). Evaluating Story Generation Systems Using Automated Linguistic Analyses. Workshop on Machine Learning for Creativity, at the 23rd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017). pdf
  • Melissa Roemmele, Paola Mardo, and Andrew Gordon (2017). Natural-language Interactive Narratives in Imaginal Exposure Therapy for Obsessive-Compulsive Disorder. Computational Linguistics and Clinical Psychology Workshop (CLPsych), at the 2017 Annual Meeting of the Association for Computational Linguistics (ACL 2017). pdf
  • Melissa Roemmele, Sosuke Kobayashi, Naoya Inoue, and Andrew Gordon (2017). An RNN-based Binary Classifier for the Story Cloze Test. Linking Models of Lexical, Sentential and Discourse-level Semantics Workshop (LSDSem), at the 2017 European Chapter of the Association for Computational Linguistics (EACL 2017). pdf
  • (Blog post) Melissa Roemmele and Michael Heilman (2016). Interpreting and Visualizing Neural Networks for Text Processing. html
  • Melissa Roemmele, Soja-Marie Morgens, Andrew Gordon, and Louis-Philippe Morency (2016). Recognizing Human Actions in the Motion Trajectories of Shapes. 2016 International Conference on Intelligent User Interfaces (IUI 2016). pdf
  • Melissa Roemmele (2016). Writing Stories with Help from Recurrent Neural Networks. Doctoral Consortium at the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16). pdf
  • Melissa Roemmele and Andrew Gordon (2015). Creative Help: A Story Writing Assistant. Eighth International Conference on Interactive Digital Storytelling (ICIDS-2015). pdf
  • Nicole Maslan, Melissa Roemmele, and Andrew Gordon (2015). One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology. Twelfth International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense-2015). pdf
  • Nicole Maslan, Melissa Roemmele, and Andrew Gordon (2015) An Integrated Evaluation of Perception, Interpretation, and Narration. Beyond the Turing Test Workshop, at the 29th AAAI Conference on Artificial Intelligence (AAAI-15). pdf
  • Andrew Gordon and Melissa Roemmele (2014). An Authoring Tool for Movies in the Style of Heider and Simmel. Seventh International Conference on Interactive Digital Storytelling (ICIDS-2014). pdf
  • Melissa Roemmele, Haley Archer-McClellan, and Andrew Gordon (2014). Triangle Charades: A Data-Collection Game for Recognizing Actions in Motion Trajectories. 2014 International Conference on Intelligent User Interfaces (IUI 2014). pdf
  • Christopher Wienberg, Melissa Roemmele, and Andrew Gordon (2013). Content-Based Similarity Measures of Weblog Authors. The 4th Annual ACM Web Science Conference (WebSci'13). pdf
  • Andrew Gordon, Zornitsa Kozareva, and Melissa Roemmele (2012). SemEval-2012 Task 7: Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning. 6th International Workshop on Semantic Evaluation (SemEval 2012), at the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2012). pdf
  • Melissa Roemmele, Cosmin Adrian Bejan, and Andrew Gordon (2011). Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning. Tenth International Symposium on Logical Formalizations of Commonsense Reasoning (Commonsense-2011). pdf