Papers by Ana Uban

4 papers
The Myth of Double-Blind Review Revisited: ACL vs. EMNLP (D19-1)

Copied to clipboard

Challenge: a double-blind review system enforces author anonymity during the review period . authors can be inferred with accuracy as high as 87% on ACL and 78% on EMNLP .
Approach: They examine how well deep learning techniques can infer authors of a paper . authors found authors can be inferred with accuracy as high as 87% on ACL and 78% on EMNLP .
Outcome: The proposed method can infer authors with 87% accuracy on ACL and 78% on EMNLP for the top 100 most prolific authors.
Verba volant, scripta volant? Don’t worry! There are computational solutions for protoword reconstruction (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for protoword reconstruction are limited to a few languages.
Approach: They propose a new database of cognate words and etymons for the five main Romance languages and apply machine learning to it.
Outcome: The proposed model achieves 90% accuracy in predicting protowords for Romance languages, surpassing state-of-the-art models and features.
It takes two to borrow: a donor and a recipient. Who’s who? (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for identifying the direction of borrowing are limited.
Approach: They propose strong benchmarks for automatic borrowing direction detection by using a borrowings dataset from the recent RoBoCoP database for five Romance languages.
Outcome: The proposed model improves the accuracy of the proposed task and proposes additional directions for future work.
RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification (2023.emnlp-main)

Copied to clipboard

Challenge: Existing databases for romance cognates are scattered, incomplete, noisy, or have uncertain availability.
Approach: They propose to use etymological information to identify Romance cognates and borrowings from dictionaries to identify their ethymology.
Outcome: The proposed method achieves 94% accuracy on two pairs of Romance languages.

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