Papers by Mackenzie Hanh Cramer

1 papers
Multimodal Conversation Structure Understanding (2026.eacl-long)

Copied to clipboard

Challenge: a new set of tasks is being developed to parse the structure of conversation . female characters are 1.2 times more likely to be cast as an addressee or side-participant .
Approach: They propose a set of tasks and release an annotated dataset for multimodal conversation structure understanding.
Outcome: The proposed model outperforms the baseline model, but performance drops when character identities are anonymized.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations