Challenge: a new study aims to extend multilingual representation learning beyond the hundred most frequent languages . current work on multilingual sentence representations has focused on training one model which handles all languages of interest .
Approach: They propose a teacher-student approach to extend existing monolingual sentence embedding space to new languages.
Outcome: The proposed model outperforms the original LASER encoder in 44 African languages . the model can be used to train multiple languages and learn new languages if they have the same training data .

Similar Papers

Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning (2023.acl-long)

Copied to clipboard

Challenge: XY-LENT: X-Y bitext enhanced Language ENcodings achieves state-of-the-art performance over 5 cross-lingual tasks within all model size bands.
Approach: They propose a method for building multilingual representation models that are competitive with existing models and more parameter efficient.
Outcome: The proposed model outperforms XLM-R XXL and is 5x and 6x smaller respectively.
Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization (2023.emnlp-industry)

Copied to clipboard

Challenge: Experimental results on multilingual similarity search and bitext mining tasks show the effectiveness of our approach.
Approach: They propose a multilingual sentence representation model that aligns different languages in a shared representation space.
Outcome: The proposed model performs better than LASER3 on similarity searches and bitext mining tasks.
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment (2024.findings-naacl)

Copied to clipboard

Challenge: Current approaches to obtain cross-lingual sentence embeddings rely on pre-trained language models that implicitly align the contextual representations of similar units of sentences in different languages.
Approach: They propose a framework that explicitly aligns words between English and eight low-resource languages by using off-the-shelf word alignment models.
Outcome: The proposed framework improves on the bitext retrieval task and in high-resource languages.
BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods to improve Neural Machine Translation (NMT) for lowresource languages are often trained on heuristically aligned or automatically mined data.
Approach: They propose to filter out imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT) instead, they propose to refine mined bitexts by automatic editing .
Outcome: The proposed method improves the quality of mined bitexts for low-resource languages by up to 8 BLEU points.
Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages (2025.acl-long)

Copied to clipboard

Challenge: XLM-R and mBART have advanced multilingualism in NLP, but low-resource languages such as Tibetan, Uyghur, Kazakh, and Mongolian are underserved.
Approach: They propose a framework for adapting multilingual encoders to text generation in extremely low-resource languages by reusing the weights between the encoder and the decoder.
Outcome: The proposed framework performs better on various downstream tasks even when compared with much larger models.
CCMatrix: Mining Billions of High-Quality Parallel Sentences on the Web (2021.acl-long)

Copied to clipboard

Challenge: Using a curated common crawl corpus, we were able to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Approach: They use 32 snapshots of a curated common crawl corpus totaling 71 billion unique sentences to mine 10.8 billion parallel sentences out of which only 2.9 billions are aligned with English.
Outcome: The proposed system outperforms the best single systems on the WMT’19 test set for English-German/Russian/Chinese and outperformed the best submission at the 2020 WAT workshop.
Mini But Mighty: Efficient Multilingual Pretraining with Linguistically-Informed Data Selection (2023.findings-eacl)

Copied to clipboard

Challenge: AfriBERTa shows that training transformer models from scratch on 1GB of data from many unrelated African languages outperforms massively multilingual models on downstream NLP tasks.
Approach: They propose that training on smaller amounts of data but from related languages could match the performance of models trained on large, unrelated data.
Outcome: The proposed model outperforms models trained on large, unrelated datasets on downstream NLP tasks.
MINERS: Multilingual Language Models as Semantic Retrievers (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks have evaluated language models to evaluate their performance across a range of embedding tasks.
Approach: They propose a benchmark to evaluate the robustness of multilingual language models in semantic retrieval tasks including bitext mining and classification via retrieval-augmented contexts.
Outcome: The proposed framework evaluates the robustness of multilingual LMs in retrieval tasks across over 200 languages, including extremely low-resource languages in challenging cross-lingual and code-switching settings.
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.
Exploiting Monolingual Data at Scale for Neural Machine Translation (D19-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) is a well-known and expensive task.
Approach: They propose a method to use target-side monolingual data for neural machine translation and propose 'synthetic bitext' they propose generating synthetic bitext by translating monolingual into the other domain using models pretrained on genuine bitext.
Outcome: The proposed approach achieves state-of-the-art results on WMT16, WMT17, WTM18 EnglishGerman translations and WTM19 GermanFrench translations.

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