Papers by Alina Maria Ciobanu

3 papers
Automatic Reconstruction of Missing Romanian Cognates and Unattested Latin Words (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods for producing related words are based on sequence labeling .
Approach: They propose a method for producing related words based on sequence labeling . they aim to fill in gaps in incomplete cognate sets in Romance languages with Latin etymology and reconstruct uncertified Latin words.
Outcome: The proposed method fills in gaps in incomplete cognate sets in Romance languages with Latin etymology and reconstructs uncertified Latin words.
Simulating Language Evolution: a Tool for Historical Linguistics (C18-2)

Copied to clipboard

Challenge: Language change across space and time is one of the main concerns in historical linguistics.
Approach: They propose a web-based tool for word form production that predicts how a word evolves in a target language.
Outcome: The proposed method is language-agnostic and does not use external knowledge except for the training word pairs.
Ab Initio: Automatic Latin Proto-word Reconstruction (C18-1)

Copied to clipboard

Challenge: Existing methods for proto-word reconstruction are time-consuming and manual, but few studies have done it . a recent study used cognates to reconstruct ancient languages from their modern counterparts .
Approach: They propose to use Latin proto-words to automate the process of proto-language reconstruction . they leverage information from all modern languages and use conditional random fields for sequence labeling .
Outcome: The proposed method improves on previous results and requires less data . it is based on word forms in multiple Romance languages and on recurrent neural networks .

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