Lisa Jin


I am pursuing a PhD at the University of Rochester advised by Daniel Gildea. My research interests include text generation and semantic parsing for structures like AMR.


I received my bachelor's degree from the University of Michigan, where I worked with Danai Koutra on dynamic graph visualization.


Lisa Jin and Daniel Gildea. “Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation.“ ACL, May 2022. To appear.

Lisa Jin, Linfeng Song, Lifeng Jin, Dong Yu, Daniel Gildea. “Hierarchical Context Tagging for Utterance Rewriting.“ AAAI, February 2022.

Lisa Jin and Daniel Gildea. “Latent Tree Decomposition Parsers for AMR-to-Text Generation.“ arXiv:2108.12304, August 2021.

Lisa Jin and Daniel Gildea. “Tree Decomposition Attention for AMR-to-Text Generation.“ arXiv:2108.12300, August 2021.

Lisa Jin and Daniel Gildea. “Generalized Shortest-Paths Encoders for AMR-to-Text Generation.“ COLING, December 2020.

Lisa Jin and Daniel Gildea. “AMR-to-Text Generation with Cache Transition Systems.“ arXiv:1912.01582, December 2019.

Lisa Jin. “Text Generation from Abstract Meaning Representation.” Area paper, University of Rochester, April 2019.

Neil Shah, Danai Koutra, Lisa Jin, Tianmin Zou, Brian Gallagher, Christos Faloutsos. “On Summarizing Large-Scale Dynamic Graphs.” Data Engineering Bulletin, September 2017, 40 (3).

Lisa Jin and Danai Koutra. “ECOviz: Comparative Visualization of Time-Evolving Network Summaries.” KDD Workshop on Interactive Data Exploration and Analytics, August 2017.

*Summaries and code can be found here.