While in the FACTS.lab, Hannah's research focused on enabling AI systems to acquire lexical knowledge for better language understanding. She collected annotated data for verb phrase ellipsis and developed models for identifying and resolving the ellipses. She also worked on investigating neg-raising inference triggers using a lexicon-scale dataset.
Gantt, William, Shabnam Behzad, Hannah An, Yunmo Chen, Aaron White, Benjamin Van Durme & Mahsa Yarmohammadi. 2024. MultiMUC: Multilingual Template Filling on MUC-4. In Yvette Graham & Matthew Purver (eds.), Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 349–368. St. Julian’s, Malta: Association for Computational Linguistics.
@inproceedings{gantt_multimuc_2024,
title = "{M}ulti{MUC}: Multilingual Template Filling on {MUC}-4",
author = "Gantt, William and
Behzad, Shabnam and
An, Hannah and
Chen, Yunmo and
White, Aaron and
Van Durme, Benjamin and
Yarmohammadi, Mahsa",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.21",
pages = "349--368",
abstract = "We introduce MultiMUC, the first multilingual parallel corpus for template filling, comprising translations of the classic MUC-4 template filling benchmark into five languages: Arabic, Chinese, Farsi, Korean, and Russian. We obtain automatic translations from a strong multilingual machine translation system and manually project the original English annotations into each target language. For all languages, we also provide human translations for key portions of the dev and test splits. Finally, we present baselines on MultiMUC both with state-of-the-art template filling models for MUC-4 and with ChatGPT. We release MUC-4 and the supervised baselines to facilitate further work on document-level information extraction in multilingual settings.",
}
Copied!
An, Hannah & Aaron White. 2020. The lexical and grammatical sources of neg-raising inferences. Proceedings of the Society for Computation in Linguistics 3(1). 220–233.
@article{an_lexical_2020,
title = {The lexical and grammatical sources of neg-raising inferences},
volume = {3},
url = {https://scholarworks.umass.edu/scil/vol3/iss1/23},
doi = {https://doi.org/10.7275/yts0-q989},
number = {1},
journal = {Proceedings of the Society for Computation in Linguistics},
author = {An, Hannah and White, Aaron},
month = jan,
year = {2020},
pages = {220--233}
}
