Papers with cross-lingual scenarios
CLEAR: Cross-Lingual Enhancement in Retrieval via Reverse-training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multilingual embedding models often struggle to capture cross-lingual alignment during training. |
| Approach: | They propose a novel loss function that leverages an English passage as a bridge to strengthen alignments between target language and English. |
| Outcome: | The proposed model improves retrieval performance across cross-lingual scenarios while minimizing performance degradation in English. |
Fine-Tuning Medium-Scale LLMs for Joint Intent Classification and Slot Filling: A Data-Efficient and Cost-Effective Solution for SMEs (2025.coling-industry)
Copied to clipboard
| Challenge: | Current techniques for user comprehension in DS depend heavily on labeled data and the data annotation process for NLU is labor-intensive and requires expert annotators. |
| Approach: | They propose to fine-tune a model for joint Intent Classification and Slot Filling with only 10% of the data. |
| Outcome: | The proposed model outperforms existing models in monolingual and cross-lingual scenarios with only 10% of the data. |
Explicit Cross-lingual Pre-training for Unsupervised Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to build initial unsupervised machine translation models with cross-lingual n-gram embeddings are inexplicit and limited. |
| Approach: | They propose a cross-lingual pre-training method that incorporates cross-linguistic training signals into pre-trained models by randomly choosing source n-grams in the input text stream. |
| Outcome: | The proposed method significantly improves the performance of unsupervised machine translation. |
Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations (2024.eacl-long)
Copied to clipboard
| Challenge: | Acoustic word embeddings are vector representations of spoken words . self-supervised learning (SSL)-based speech models are popular for speech recognition . |
| Approach: | They explore the effectiveness of the Correspondence Auto-Encoder to obtain improved AWEs . they use self-supervised learning on large amounts of unlabelled speech data . |
| Outcome: | The Correspondence Auto-Encoder (CAE) model outperforms MFCC models on language discrimination . the model achieves best results in Polish, Portuguese, Spanish, French, and English . |
Enhancing Polyglot Voices by Leveraging Cross-Lingual Fine-Tuning in Any-to-One Voice Conversion (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in speech synthesis have improved the quality of polyglot voices. |
| Approach: | They propose a cross-lingual any-to-one voice conversion system that preserves the source accent without multilingual data from the target speaker. |
| Outcome: | The proposed system preserves source accent without multilingual data from target speaker and reduces training data requirements. |
Self-Attention with Cross-Lingual Position Representation (2020.acl-main)
Copied to clipboard
| Challenge: | Position encoding (PE) is used to preserve word order information for natural language processing tasks, generating fixed position indices for input sequences. |
| Approach: | They propose to augment SANs with cross-lingual position representations to model bilingually aware latent structure for the input sentence. |
| Outcome: | The proposed model significantly improves translation quality over baselines on EnglishGerman, JapaneseEnglish, and ChineseEnglish translation tasks. |
MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAG (2025.findings-emnlp)
Copied to clipboard
Nguyen Manh Hieu, Vu Lam Anh, Hung Pham Van, Nam Le Hai, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen
| Challenge: | Recent advances in Graph-based RAG (GRAG) frameworks focus on knowledge graphs for cross-lingual retrieval. |
| Approach: | They propose a new GRAG framework for cross-lingual question answering . MaGiX constructs a multi-granular cross-linguistic knowledge graph using fine-grained attribute descriptions and cross-synonym edges. |
| Outcome: | The proposed framework outperforms prior GRAG systems in retrieval accuracy and generation quality. |
How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on instruction-tuned Large Language Models has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to human evaluation. |
| Approach: | They perform a meta-evaluation of automatic methods and assess their reliability across a broad range of tasks. |
| Outcome: | The proposed method is unreliable in free-form generation tasks and cross-lingual scenarios. |
Czech Dataset for Complex Aspect-Based Sentiment Analysis Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | 3.1K reviews are manually annotated for aspect-based sentiment analysis (ABSA) ABSA is a fine-grained task that aims to identify the sentiment associated with each aspect or characteristic of a text. |
| Approach: | They propose a new Czech dataset for aspect-based sentiment analysis . the new dataset is built upon the older Czech dataset . authors provide 24M reviews without annotations suitable for unsupervised learning . |
| Outcome: | The proposed dataset is built upon the older dataset, but is specifically designed for more complex tasks. |