English
Related papers

Related papers: 2D Matryoshka Sentence Embeddings

200 papers

Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task…

Large language models (LLMs) generate high-dimensional embeddings that capture rich semantic and syntactic information. However, high-dimensional embeddings exacerbate computational complexity and storage requirements, thereby hindering…

Computation and Language · Computer Science 2025-10-15 Biao Zhang , Lixin Chen , Tong Liu , Bo Zheng

2D Matryoshka Training is an advanced embedding representation training approach designed to train an encoder model simultaneously across various layer-dimension setups. This method has demonstrated higher effectiveness in Semantic Text…

Information Retrieval · Computer Science 2024-11-27 Shuai Wang , Shengyao Zhuang , Bevan Koopman , Guido Zuccon

Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply truncating the resulting vectors at sizes pre-determined at…

Machine Learning · Computer Science 2026-05-29 Sotaro Takeshita , Yurina Takeshita , Simone Paolo Ponzetto , Daniel Ruffinelli

The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitive computational costs, a narrow linguistic focus that neglects most of the world's…

Computation and Language · Computer Science 2026-05-15 Ziyin Zhang , Zihan Liao , Hang Yu , Peng Di , Rui Wang

Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…

Computation and Language · Computer Science 2019-01-17 Myeongjun Jang , Pilsung Kang

Large language models (LLMs) have recently shown strong potential in audio-visual speech recognition (AVSR), but their high computational demands and sensitivity to token granularity limit their practicality in resource-constrained…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-07 Umberto Cappellazzo , Minsu Kim , Pingchuan Ma , Honglie Chen , Xubo Liu , Stavros Petridis , Maja Pantic

Embeddings from Large Language Models (LLMs) have emerged as critical components in various applications, particularly for information retrieval. While high-dimensional embeddings generally demonstrate superior performance as they contain…

Computation and Language · Computer Science 2024-07-31 Jinsung Yoon , Raj Sinha , Sercan O Arik , Tomas Pfister

Large language models (LLMs) provide powerful foundations to perform fine-grained text re-ranking. However, they are often prohibitive in reality due to constraints on computation bandwidth. In this work, we propose a \textbf{flexible}…

Computation and Language · Computer Science 2025-01-28 Zheng Liu , Chaofan Li , Shitao Xiao , Chaozhuo Li , Defu Lian , Yingxia Shao

Retrievers are a key bottleneck in Temporal Retrieval-Augmented Generation (RAG) systems: failing to retrieve temporally relevant context can degrade downstream generation, regardless of LLM reasoning. We propose Temporal-aware Matryoshka…

Information Retrieval · Computer Science 2026-01-12 Tuan-Luc Huynh , Weiqing Wang , Trung Le , Thuy-Trang Vu , Dragan Gašević , Yuan-Fang Li , Thanh-Toan Do

Speakers of under-represented languages face both a language barrier, as most online knowledge is in a few dominant languages, and a modality barrier, since information is largely text-based while many languages are primarily oral. We…

Computation and Language · Computer Science 2026-04-22 Yaya Sy , Dioula Doucouré , Christophe Cerisara , Irina Illina

2D Matryoshka training enables a single embedding model to generate sub-network representations across different layers and embedding dimensions, offering adaptability to diverse computational and task constraints. However, its…

Information Retrieval · Computer Science 2025-06-02 Shengyao Zhuang , Shuai Wang , Fabio Zheng , Bevan Koopman , Guido Zuccon

Many large-scale systems rely on high-quality deep representations (embeddings) to facilitate tasks like retrieval, search, and generative modeling. Matryoshka Representation Learning (MRL) recently emerged as a solution for adaptive…

Machine Learning · Computer Science 2025-05-21 Tiansheng Wen , Yifei Wang , Zequn Zeng , Zhong Peng , Yudi Su , Xinyang Liu , Bo Chen , Hongwei Liu , Stefanie Jegelka , Chenyu You

This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a…

Computation and Language · Computer Science 2017-03-10 Zhouhan Lin , Minwei Feng , Cicero Nogueira dos Santos , Mo Yu , Bing Xiang , Bowen Zhou , Yoshua Bengio

This work presents a novel framework for training Arabic nested embedding models through Matryoshka Embedding Learning, leveraging multilingual, Arabic-specific, and English-based models, to highlight the power of nested embeddings models…

Computation and Language · Computer Science 2024-08-02 Omer Nacar , Anis Koubaa

Open-vocabulary keyword spotting (KWS) with text-based enrollment has emerged as a flexible alternative to fixed-phrase triggers. Prior utterance-level matching methods, from an embedding-learning standpoint, learn embeddings at a single…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Youngmoon Jung , Myunghun Jung , Joon-Young Yang , Yong-Hyeok Lee , Jaeyoung Roh , Hoon-Young Cho

Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) offers a flexible inference paradigm through nested…

Computation and Language · Computer Science 2026-04-28 Phung Gia Huy , Hai An Vu , Minh-Phuc Truong , Thang Duc Tran , Linh Ngo Van , Thanh Hong Nguyen , Trung Le

Short-utterance speaker verification remains challenging due to limited speaker-discriminative cues in short speech segments. While existing methods focus on enhancing speaker encoders, the embedding learning strategy still forces a single…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-21 Youngmoon Jung , Joon-Young Yang , Ju-ho Kim , Jaeyoung Roh , Chang Woo Han , Hoon-Young Cho

There is a lot of research interest in encoding variable length sentences into fixed length vectors, in a way that preserves the sentence meanings. Two common methods include representations based on averaging word vectors, and…

Computation and Language · Computer Science 2017-02-10 Yossi Adi , Einat Kermany , Yonatan Belinkov , Ofer Lavi , Yoav Goldberg

In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dense embeddings are often extremely high-dimensional, incurring…

Machine Learning · Computer Science 2026-03-03 Lixuan Guo , Yifei Wang , Tiansheng Wen , Yifan Wang , Aosong Feng , Bo Chen , Stefanie Jegelka , Chenyu You
‹ Prev 1 2 3 10 Next ›