ACL Findings2025
Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic languages
Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki, Pankaj Wasnik
Abstract
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.
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.
Lineage
- Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models cites Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
- Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings cites SPECTER: Document-level Representation Learning using Citation-informed Transformers
Builds on4
- Neighborhood Contrastive Learning for Scientific Document Representations with Citation EmbeddingsMalte Ostendorff, Nils Rethmeier, Isabelle Augenstein, Bela Gipp et al.EMNLP 2022 · 46 citations
- Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language ModelsShuang Li, Jiangjie Chen, Siyu Yuan, Xinyi Wu et al.AAAI 2024 · 44 citations
- SPECTER: Document-level Representation Learning using Citation-informed TransformersArman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey et al.ACL 2020 · 20 citations
- Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine TranslationVerna Dankers, Christopher G. Lucas, Ivan TitovACL 2022
Related papers
- Easy as PIE? Identifying Multi-Word Expressions with LLMsKai Golan Hashiloni, Ofri Hefetz, Kfir BarEMNLP 2025
- IEKG: A Commonsense Knowledge Graph for Idiomatic ExpressionsZiheng Zeng, Kellen Tan Cheng, Srihari Venkat Nanniyur, Jianing Zhou et al.EMNLP 2023 · 1 citation
- Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss WeightingEmmy Liu, Aditi Chaudhary, Graham NeubigEMNLP 2023 · 2 citations
- Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet LossWei He, Marco Idiart, Carolina Scarton, Aline VillavicencioACL Findings 2024 · 1 citation
- Idiomatic Expression Paraphrasing without Strong SupervisionJianing Zhou, Ziheng Zeng, Hongyu Gong, Suma BhatAAAI 2022 · 12 citations
