Abstract
This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible to estimate the reliability of low-resource embeddings using corpus similarity measures that remain robust on small amounts of data. These findings have significant implications for the evaluation of truly low-resource languages in which such systematic downstream validation methods are not possible because of data limitations.- Anthology ID:
- 2022.lrec-1.693
- Volume:
- Proceedings of the Thirteenth Language Resources and Evaluation Conference
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Editors:
- Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 6461–6470
- Language:
- URL:
- https://aclanthology.org/2022.lrec-1.693
- DOI:
- Cite (ACL):
- Jonathan Dunn, Haipeng Li, and Damian Sastre. 2022. Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6461–6470, Marseille, France. European Language Resources Association.
- Cite (Informal):
- Predicting Embedding Reliability in Low-Resource Settings Using Corpus Similarity Measures (Dunn et al., LREC 2022)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2022.lrec-1.693.pdf
- Code
- jonathandunn/corpus_similarity