paper-with-me

Papers

LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation

2023-02-16 · Zhuoyuan Mao, Tetsuji Nakagawa

Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment. However, these large-scale models can suffer from inference speed and computation overhead. This study systematically explores learning language-agnostic sentence embeddings with lightweight models. We demonstrate that a thin-deep encoder can construct robust low-dimensional sentence embeddings for 109 languages. With our proposed distillation methods, we achieve further improvements by incorporating knowledge from a teacher model. Empirical results on Tatoeba, United Nations, and BUCC show the effectiveness of our lightweight models. We release our lightweight language-agnostic sentence embedding models LEALLA on TensorFlow Hub.

📄 PDF Abstract BibTeX arXiv:2302.08387

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationSentenceSentence EmbeddingSentence-EmbeddingSentence Embeddings

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SONAR-SLT: Multilingual Sign Language Translation via Language-Agnostic Sentence Embedding Supervision

2025-10-22 · Yasser Hamidullah, Shakib Yazdani, Cennet Oguz, Josef van Genabith 외 arxiv

Sign language translation (SLT) is typically trained with text in a single spoken language, which limits scalability and cross-language generalization. Earlier approaches have replaced gloss supervision with text-based s…

Sign Language Translation

Are Language-Agnostic Sentence Representations Actually Language-Agnostic?

2021-09-01 · RANLP 2021 9 · Yu Chen, Tania Avgustinova

With the emergence of pre-trained multilingual models, multilingual embeddings have been widely applied in various natural language processing tasks. Language-agnostic models provide a versatile way to convert linguistic…

SentenceSentence EmbeddingsTranslation

When Does Complexity Conditioning Help a Frozen Sentence Embedding? A Controlled Study of Per-Sentence and Pair-Level Difficulty Adaptation

2026-06-02 · Suhwan Hwang arxiv

A common intuition is that sentence embeddings should adapt to the difficulty of the input. We test this intuition in a controlled, multi-seed setting: a lightweight post-encoder adapter attaches to a frozen Qwen3-Embedd…

Multilingual Sentence Transformer as A Multilingual Word Aligner

2023-01-28 · Weikang Wang, Guanhua Chen, Hanqing Wang, Yue Han 외

Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction. However, these methods usually start from mBERT or XLM-R. In this paper, we investigate whether mul…

SentenceWord AlignmentXLM-R

Static Fuzzy Bag-of-Words: a lightweight sentence embedding algorithm

2023-04-06 · Matteo Muffo, Roberto Tedesco, Licia Sbattella, Vincenzo Scotti

The introduction of embedding techniques has pushed forward significantly the Natural Language Processing field. Many of the proposed solutions have been presented for word-level encoding; anyhow, in the last years, new …

Semantic Textual SimilaritySentenceSentence EmbeddingSentence-Embedding+1