Papers with cross-lingual tasks

25 papers
Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data (2023.acl-short)

Copied to clipboard

Challenge: Zero-shot cross-lingual transfer is enabled by pairing the language adapter in the target language with an appropriate task adapter within a source language.
Approach: They propose to use unlabeled text to enhance zero-shot transfer by pairing language adapters with task adapters in a target language.
Outcome: The proposed framework improves on three cross-lingual tasks with up to 11% relative improvement in Named Entity Recognition (NER), Question Answering (QA) and Natural Language Inference (NLI).
COSY: COunterfactual SYntax for Cross-Lingual Understanding (2021.acl-long)

Copied to clipboard

Challenge: Pre-trained multilingual language models suffer from a large performance gap between source and target languages . e.g., multilingual-BERT models are widely used in cross-lingual tasks .
Approach: They propose a language-agnostic approach to integrate universal syntax into language models . they use SYntax-aware networks and a COunterfactual training method .
Outcome: The proposed model achieves state-of-the-art performance on natural language inference and question answering without auxiliary training data.
Mixed-Lingual Pre-training for Cross-lingual Summarization (2020.aacl-main)

Copied to clipboard

Challenge: Cross-lingual summarization (CLS) aims at producing a summary in the target language for an article in the source language.
Approach: They propose a mixed-lingual pre-training scheme that leverages both cross-lingual tasks such as translation and monolingual tasks like masked language models.
Outcome: The proposed model improves on the translation and masked language models with no task-specific components and saves memory.
Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent multilingual pre-trained models have been demonstrated effective in many cross-lingual tasks.
Approach: They propose a framework that leverages code-switched data with multi-view learning to fine-tune XLM-R.
Outcome: The proposed model achieves state-of-the-art on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks.
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models? (2021.acl-short)

Copied to clipboard

Challenge: Recent studies have shown that cross-lingual transfer learning in pre-trained multilingual models could be improved further by incorporating parallel data.
Approach: They propose to integrate parallel data into mT5 pre-training to improve results on downstream multilingual and cross-lingual tasks.
Outcome: The proposed model improves cross-lingual transfer significantly in small fine-tuning datasets and small model sizes.
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment (2025.acl-long)

Copied to clipboard

Challenge: Multilingual sentence encoders are often trained to map sentences from different languages into a shared semantic vector space . cross-lingual alignment training distorts optimal monolingual structure of semantic spaces of individual languages . a modular solution can be used for cross-linguistic tasks such as cross-language semantic similarity and zero-shot transfer .
Approach: They propose a modular training system that embeds sentences from different languages into a shared semantic vector space.
Outcome: The proposed solution achieves better performance across all tasks compared to monolithic models.
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit impressive performance on a variety of tasks from text summarization to zero-shot common-sense reasoning.
Approach: They propose to manipulate the embedding space of mLLMs by manipulating its activations to steer generation into the desired direction.
Outcome: The proposed model interventions improves alignment of cross-lingual representations in multilingual large language models with up to 2x improvements in top-1 accuracy on cross-linguistic retrieval tasks.
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs (2021.emnlp-main)

Copied to clipboard

Challenge: Multilingual T5 pretrains a sequence-to-sequence model on monolingual texts, but it has shown promising results on many cross-lingual tasks.
Approach: They propose a partially non-autoregressive objective for text-to-text pre-training and propose mT6 to improve cross-lingual transferability over multilingual T5.
Outcome: The proposed model improves cross-lingual transferability over existing models.
Structural Contrastive Pretraining for Cross-Lingual Comprehension (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to train multilingual language models using pretraining tasks like mask language modeling have yielded promising results on a wide range of downstream tasks.
Approach: They propose a new task to align the structural words in a parallel sentence, enhancing models’ ability to comprehend cross-lingual representations.
Outcome: The proposed task improves model's ability to comprehend cross-lingual representations by increasing the frequency of negative pairings.
Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial Labels (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to train pre-trained language models for zero-shot cross-lingual tasks are noisy and lack confidence.
Approach: They propose an uncertainty-aware cross-lingual transfer framework with pseudo-partial-label to maximize the utilization of unlabeled data by reducing noise.
Outcome: The proposed framework outperforms baselines on named entity recognition and natural language inference tasks on 40 languages.
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies have suggested that bilingual lexicon induction is influenced by the (dis)similarity of the languages at hand.
Approach: They propose to measure the isomorphism of monolingual embedding spaces based on their spectra and introduce isometric measures to measure their similarity.
Outcome: The proposed measures outperform standard isomorphism measures while being more tractable and easier to interpret.
Towards Debiasing Translation Artifacts (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies show translation artifacts in translations influence performance of cross-lingual tasks.
Approach: They propose a method to reduce translation artifacts by extending an established bias-removal technique.
Outcome: The proposed method reduces translationese at sentence and word level . it is the first study to debias translations on a natural language inference task .
VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation (2021.acl-long)

Copied to clipboard

Challenge: Existing work in multilingual pretraining relies on the shared vocabulary and bilingual contexts to encourage the correlation across languages.
Approach: They propose to plug a cross-attention module into a Transformer encoder to explicitly build the interdependence between languages.
Outcome: The proposed model outperforms existing models on XTREME and English-to-French translation datasets.
CINO: A Chinese Minority Pre-trained Language Model (2022.coling-1)

Copied to clipboard

Challenge: Existing multilingual pre-trained language models do not perform well on some low-resource languages.
Approach: They propose a multilingual pre-trained language model for Chinese minority languages . they collect documents from Wikipedia and construct two classification datasets .
Outcome: The proposed model outperforms baseline models on various classification tasks.
Cross-Lingual NLU: Mitigating Language-Specific Impact in Embeddings Leveraging Adversarial Learning (2024.lrec-main)

Copied to clipboard

Challenge: Low-resource languages and computational expenses pose significant challenges in the domain of large language models.
Approach: They propose a novel approach that uses adversarial techniques to mitigate the impact of language-specific information in contextual embeddings generated by large multilingual language models.
Outcome: The proposed approach excels in zero-shot scenarios for Latin languages like Spanish, but fails to perform for languages distant from English, such as Thai and Persian.
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to learn cross-lingual word embeddings are sense agnostic . a novel framework to align contextual embeddables at the sense level is proposed .
Approach: They propose a framework to align contextual embeddings at the sense level by leveraging cross-lingual signal from bilingual dictionaries only.
Outcome: The proposed framework improves word sense disambiguation tasks by leveraging bilingual dictionaries . compared with baseline results, the proposed models achieve 0.52%, 2.09% and 1.29% performance improvements .
Vocabulary-informed Language Encoding (2022.coling-1)

Copied to clipboard

Challenge: A Multilingual model relies on language encodings to identify input languages . a method to compute a vocabulary-informed language coding can improve multilingual models .
Approach: They propose a method to compute a vocabulary-informed language encoding as the language representation for a required language.
Outcome: The proposed method improves performance on unsupervised translation and cross-lingual embedding.
LAReQA: Language-Agnostic Answer Retrieval from a Multilingual Pool (2020.emnlp-main)

Copied to clipboard

Challenge: LAReQA tests for “strong” cross-lingual alignment, requiring semantically related cross-language pairs to be closer in representation space than unrelated same-language pair.
Approach: They propose a new benchmark for language-agnostic answer retrieval from a multilingual candidate pool that tests for "strong" cross-lingual alignment . they augment training data via machine translation and find that model performance is improved by augmenting training data through machine translation .
Outcome: The proposed task is based on multilingual BERT (mBERT) and XLM-R.
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Copied to clipboard

Challenge: XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach: They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome: The proposed dataset is labeled in English and includes only natural language understanding tasks.
Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation (2021.emnlp-main)

Copied to clipboard

Challenge: Recent pre-trained language models have achieved remarkable zero-shot performance . we propose a self-learning framework that utilizes unlabeled data of target languages .
Approach: They propose a self-learning framework that utilizes unlabeled data of target languages to select silver labels for cross-lingual transfer tasks.
Outcome: The proposed framework outperforms baseline models on two cross-lingual tasks by 10 F1 on average and 2.5 accuracy on natural language inference (NLI).
Language Embeddings for Typology and Cross-lingual Transfer Learning (2021.acl-long)

Copied to clipboard

Challenge: Recent efforts to leverage multilingual datasets highlight potential of multilingual models that can perform well across various languages.
Approach: They propose to generate language representations that capture relationships among languages and evaluate them using WALS and two extrinsic tasks.
Outcome: The proposed model can be leveraged in cross-lingual tasks without parallel data . the proposed model is based on the World Atlas of Language Structures (WALS) and two extrinsic tasks .
KIT-Multi: A Translation-Oriented Multilingual Embedding Corpus (L18-1)

Copied to clipboard

Challenge: Cross-lingual word embeddings are representations of words across languages in a shared continuous vector space.
Approach: They propose a multilingual word embedding corpus which is acquired by neural machine translation and is based on monolingual data.
Outcome: The proposed method is competitive with existing methods but on the cross-lingual document classification task, it obtains the best figures.
LexCLiPR: Cross-Lingual Paragraph Retrieval from Legal Judgments (2025.acl-long)

Copied to clipboard

Challenge: Existing work on IR focus on retrieving entire cases rather than precise, paragraph-level information.
Approach: They propose a cross-lingual dataset for paragraph-level retrieval from ECtHR judgments . they evaluate retrieval models in a zero-shot setting and use multilingual case law guides .
Outcome: The proposed model excels in cross-lingual retrieval, while siamese architectures are better suited for monolingual tasks.
A Joint Matrix Factorization Analysis of Multilingual Representations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have demonstrated that pre-trained models acquire and incorporate linguistic knowledge in their multilingual representations.
Approach: They propose a tool for comparing latent representations of multilingual and monolingual models . they use joint matrix factorization to analyze multiple sets of representations in a joint manner .
Outcome: The proposed tool analyzes latent representations of multilingual and monolingual models . it shows that language properties influence the factorization outputs .
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining (2026.acl-long)

Copied to clipboard

Challenge: Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining.
Approach: They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions.
Outcome: The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations