Lune

ACL Findings2024

It takes two to borrow: a donor and a recipient. Who's who?

Liviu P. Dinu, Ana Sabina Uban, Anca P. Dinu, Ioan-Bogdan Iordache, Simona Georgescu, Laurentiu Zoicas

Abstract

We address the open problem of automatically identifying the direction of lexical borrowing, given word pairs in the donor and recipient languages. We propose strong benchmarks for this task, by applying a set of machine learning models. We extract and publicly release a comprehensive borrowings dataset from the recent RoBoCoP cognates and borrowings database (Dinu et al., 2023) for five Romance languages. We experiment on this dataset with both graphic and phonemic representations and with different features, models and architectures. We interpret the results, in terms of F1 score, commenting on the influence of features and model choice, of the imbalanced data and of the inherent difficulty of the task for particular language pairs. We show that automatically determining the direction of borrowing is a feasible task, and propose additional directions for future work.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification cites Probing Multilingual Cognate Prediction Models
  • Verba volant, scripta volant? Don't worry! There are computational solutions for protoword reconstruction cites RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate Identification
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Verba volant, scripta volant? Don't worry! There are computational solutions for protoword reconstructionLiviu P. Dinu, Ana Sabina Uban, Alina Maria Cristea, Ioan-Bogdan Iordache et al.EMNLP 2024

Builds on4

  1. Automatic Discrimination between Inherited and Borrowed Latin Words in Romance LanguagesAlina Maria Cristea, Liviu P. Dinu, Simona Georgescu, Mihnea-Lucian Mihai et al.EMNLP Findings 2021 · 6 citations
  2. Probing Multilingual Cognate Prediction ModelsClémentine Fourrier, Benoît SagotACL Findings 2022 · 4 citations
  3. RoBoCoP: A Comprehensive ROmance BOrrowing COgnate Package and Benchmark for Multilingual Cognate IdentificationLiviu P. Dinu, Ana Sabina Uban, Alina Maria Cristea, Anca P. Dinu et al.EMNLP 2023 · 2 citations
  4. Sequence Models for Computational Etymology of BorrowingsWinston Wu, Kevin Duh, David YarowskyACL Findings 2021 · 1 citation

Related papers

  1. Friend or Foe? A Computational Investigation of Semantic False Friends across Romance LanguagesAna Sabina Uban, Liviu P. Dinu, Ioan-Bogdan Iordache, Simona Georgescu et al.EMNLP 2025
  2. ConLoan: A Contrastive Multilingual Dataset for Evaluating LoanwordsSina Ahmadi, Micha David Hess, Elena Álvarez Mellado, Alessia Battisti et al.ACL 2025
  3. Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task?Clémentine Fourrier, Rachel Bawden, Benoît SagotACL Findings 2021 · 11 citations
  4. Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to ModelingElena Álvarez Mellado, Constantine LignosACL 2022 · 13 citations
  5. False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and SpanishMarta Vázquez Abuín, José Camacho-Collados, Marcos GarcíaACL 2026
Dusk over the sea between two cliffs drawn in fine vertical lines