The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasks (2025.findings-acl)
Copied to clipboard
| Challenge: | Translation-based strategies for cross-lingual transfer XLT include label projection . word aligners (WAs) are commonly used for label projection, but low-level design decisions for using them have not been investigated . |
| Approach: | They revisit word aligners (WAs) for label projection and propose a new projection strategy that outperforms WAs. |
| Outcome: | The proposed projection strategy outperforms marker-based methods in token classification tasks. |
Similar Papers
TransAlign: Machine Translation Encoders are Strong Word Aligners, Too (2025.findings-emnlp)
Copied to clipboard
| Challenge: | translation-based approaches to cross-lingual transfer (XLT) are limited. |
| Approach: | They propose a word aligner that utilizes the encoder of a massively multilingual MT model. |
| Outcome: | The proposed word aligner outperforms existing WA and state-of-the-art non-WA-based methods in token classification tasks. |
Frustratingly Easy Label Projection for Cross-lingual Transfer (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve cross-lingual transfer performance are based on word alignment, but no empirical studies have evaluated their effectiveness or limitations. |
| Approach: | They propose a mark-then-translate method that integrates translation and projection by inserting special markers around the labeled spans in the original sentence. |
| Outcome: | The proposed method outperforms word alignment-based methods in 57 languages and three tasks. |
The Effects of Language Token Prefixing for Multilingual Machine Translation (2022.aacl-short)
Copied to clipboard
| Challenge: | In recent years, the field has moved towards large neural models either translating from or into many languages. |
| Approach: | They propose to prefix language tokens onto a source or target sequence to improve translation performance. |
| Outcome: | The proposed methods improve translation performance and source side prefixes improve translation. |
Hierarchical Mapping for Crosslingual Word Embedding Alignment (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing strategies that map word embeddings into a crosslingual space are biased towards the choice of the pivot language. |
| Approach: | They propose to map any two languages into a different middle space by learning mappings across languages in a hierarchical way. |
| Outcome: | The proposed strategy significantly improves vocabulary induction scores in all existing benchmarks and in a new non-English–centered benchmark. |
Constraining word alignments with posterior regularization for label transfer (2022.naacl-industry)
Copied to clipboard
| Challenge: | Unsupervised word alignments are not always possible in industrial NLP pipelines, where multilingual annotation guidelines are complex and deviate from semantic consistency due to various factors. |
| Approach: | They propose to constrain word alignment models to remain consistent with both source and target annotation guidelines by leveraging posterior regularization and labeled examples. |
| Outcome: | The proposed model improves on the multiATIS++ dataset over AWESoME, and even a small amount of target language annotations can help. |
Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on Aspect-based sentiment analysis (ABSA) focus on English texts, but handling it in resource-poor languages remains a challenge. |
| Approach: | They propose an unsupervised cross-lingual transfer method for the Aspect-based sentiment analysis task . they propose an aspect code-switching mechanism to augment training data with code-linked bilingual sentences . |
| Outcome: | The proposed method preserves task-specific knowledge in the target language. |
Just Use XML: Revisiting Joint Translation and Label Projection (2026.findings-acl)
Copied to clipboard
| Challenge: | Label projection is an effective technique for cross-lingual transfer, extending span-annotated datasets from high-resource languages to low-resourced ones. |
| Approach: | They propose a framework that performs translation and label projection via XML tags. |
| Outcome: | The proposed framework outperforms baselines and improves translation quality across languages and annotation complexity. |
To Translate or Not to Translate: A Systematic Investigation of Translation-Based Cross-Lingual Transfer to Low-Resource Languages (2024.naacl-long)
Copied to clipboard
| Challenge: | XLT with multilingual language models is superfluous, says a new study . mBERT, XLM-R and mT5 are effective for cross-lingual transfer, authors say . |
| Approach: | They propose to use multilingual language models to improve cross-lingual transfer (XLT) they propose to add reliable translations to training data for XLT even for non-MT languages . |
| Outcome: | The proposed approaches outperform zero-shot XLT with mLMs, the authors show . the authors believe their findings warrant a broader inclusion of more robust translation-based baselines in XL research. |
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment (2021.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that denoising word alignment improves cross-lingual transferability . most applications and resources are still English-centric, making non-English users hard to access. |
| Approach: | They propose to denoise word alignment as a cross-lingual pre-training task . they first self-label word alignments for parallel sentences and then mask tokens . |
| Outcome: | The proposed model improves cross-lingual transferability on token-level tasks, especially on question answering, and structured prediction. |
Language Directions in Multilingual LLMs: A Layer-wise Diagnostic Study of Token Alignment and Pretraining Imprint (2026.acl-srw)
Copied to clipboard
| Challenge: | Using a unified probing framework, we analyze six multilingual LLMs across five languages. |
| Approach: | They analyze multilingual representations across five languages and analyze their behavior . they find that accuracy rises by +73.5 to +80.7 points from L0 to L1 on average . |
| Outcome: | The proposed framework enables a consistent and substantial early jump in accuracy across models . the token–language alignment measures where vocabulary sharing peaks . |