Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss
He, Wei, Idiart, Marco, Scarton, Carolina, Villavicencio, Aline
–arXiv.org Artificial Intelligence
Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words, but also due to the scarcity of relevant data resources, and their impact on the performance of downstream tasks such as machine translation and simplification. In this paper we propose an approach to model idiomaticity effectively using a triplet loss that incorporates the asymmetric contribution of components words to an idiomatic meaning for training language models by using adaptive contrastive learning and resampling miners to build an idiomatic-aware learning objective. Our proposed method is evaluated on a SemEval challenge and outperforms previous alternatives significantly in many metrics.
arXiv.org Artificial Intelligence
Jun-21-2024
- Country:
- South America
- Brazil > Rio Grande do Sul (0.04)
- Colombia > Meta Department
- Villavicencio (0.06)
- Oceania > Australia
- North America
- Mexico (0.04)
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- Ohio > Franklin County
- Columbus (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Colorado > Denver County
- Denver (0.04)
- Washington > King County
- Canada > Ontario
- Toronto (0.04)
- Europe
- Germany > Berlin (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Denmark > Capital Region
- Copenhagen (0.04)
- Croatia > Dubrovnik-Neretva County
- Dubrovnik (0.04)
- Asia
- Singapore (0.04)
- China > Hong Kong (0.04)
- Middle East > UAE
- Abu Dhabi Emirate > Abu Dhabi (0.04)
- Japan > Honshū
- Kansai > Osaka Prefecture > Osaka (0.04)
- South America
- Genre:
- Research Report (0.82)
- Technology: