Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages
This work addresses idiomatic translation challenges for Indic languages, which is an incremental improvement over existing methods.
The paper tackled the problem of translating idioms and multi-word expressions by addressing cultural nuances and one-to-many mappings, proposing IdiomCE, an adaptive GNN-based method that improved translation quality for English to Indian languages, as demonstrated with significant gains on reference-less metrics.
Translating multi-word expressions (MWEs) and idioms requires a deep understanding of the cultural nuances of both the source and target languages. This challenge is further amplified by the one-to-many nature of idiomatic translations, where a single source idiom can have multiple target-language equivalents depending on cultural references and contextual variations. Traditional static knowledge graphs (KGs) and prompt-based approaches struggle to capture these complex relationships, often leading to suboptimal translations. To address this, we propose IdiomCE, an adaptive graph neural network (GNN) based methodology that learns intricate mappings between idiomatic expressions, effectively generalizing to both seen and unseen nodes during training. Our proposed method enhances translation quality even in resource-constrained settings, facilitating improved idiomatic translation in smaller models. We evaluate our approach on multiple idiomatic translation datasets using reference-less metrics, demonstrating significant improvements in translating idioms from English to various Indian languages.