Abstract
Compositional generalisation refers to the ability to understand and generate a potentially infinite number of novel meanings using a finite group of known primitives and a set of rules to combine them. The degree to which artificial neural networks can learn this ability is an open question. Recently, some evaluation methods and benchmarks have been proposed to test compositional generalisation, but not many have focused on the morphological level of language. We propose an application of the previously developed distribution-based compositionality assessment method to assess morphological generalisation in NLP tasks, such as machine translation or paraphrase detection. We demonstrate the use of our method by comparing translation systems with different BPE vocabulary sizes. The evaluation method we propose suggests that small vocabularies help with morphological generalisation in NMT.- Anthology ID:
- 2023.nodalida-1.75
- Volume:
- Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
- Month:
- May
- Year:
- 2023
- Address:
- Tórshavn, Faroe Islands
- Editors:
- Tanel Alumäe, Mark Fishel
- Venue:
- NoDaLiDa
- SIG:
- Publisher:
- University of Tartu Library
- Note:
- Pages:
- 738–751
- Language:
- URL:
- https://aclanthology.org/2023.nodalida-1.75
- DOI:
- Cite (ACL):
- Anssi Moisio, Mathias Creutz, and Mikko Kurimo. 2023. Evaluating Morphological Generalisation in Machine Translation by Distribution-Based Compositionality Assessment. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 738–751, Tórshavn, Faroe Islands. University of Tartu Library.
- Cite (Informal):
- Evaluating Morphological Generalisation in Machine Translation by Distribution-Based Compositionality Assessment (Moisio et al., NoDaLiDa 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-07/2023.nodalida-1.75.pdf