paper-with-me

홈 › Papers

Towards Building Efficient Sentence BERT Models using Layer Pruning

2024-09-21 · Anushka Shelke, Riya Savant, Raviraj Joshi

This study examines the effectiveness of layer pruning in creating efficient Sentence BERT (SBERT) models. Our goal is to create smaller sentence embedding models that reduce complexity while maintaining strong embedding similarity. We assess BERT models like Muril and MahaBERT-v2 before and after pruning, comparing them with smaller, scratch-trained models like MahaBERT-Small and MahaBERT-Smaller. Through a two-phase SBERT fine-tuning process involving Natural Language Inference (NLI) and Semantic Textual Similarity (STS), we evaluate the impact of layer reduction on embedding quality. Our findings show that pruned models, despite fewer layers, perform competitively with fully layered versions. Moreover, pruned models consistently outperform similarly sized, scratch-trained models, establishing layer pruning as an effective strategy for creating smaller, efficient embedding models. These results highlight layer pruning as a practical approach for reducing computational demand while preserving high-quality embeddings, making SBERT models more accessible for languages with limited technological resources.

📄 PDF Abstract BibTeX arXiv:2409.14168

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language InferenceSemantic Textual SimilaritySentenceSentence EmbeddingSentence-EmbeddingSTS

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

A Sliding Layer Merging Method for Efficient Depth-Wise Pruning in LLMs

2025-02-26 · Xuan Ding, Rui Sun, Yunjian Zhang, Xiu Yan 외

Compared to width-wise pruning, depth-wise pruning can significantly accelerate inference in resource-constrained scenarios. However, treating the entire Transformer layer as the minimum pruning unit may degrade model pe…

On the Effect of Dropping Layers of Pre-trained Transformer Models

2020-04-08 · Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Preslav Nakov

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally corre…

Knowledge DistillationSentenceSentence Similarity

On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages

2025-01-01 · Mayur Shirke, Amey Shembade, Madhushri Wagh, Pavan Thorat 외

This study explores the effectiveness of layer pruning for developing more efficient BERT models tailored to specific downstream tasks in low-resource languages. Our primary objective is to evaluate whether pruned BERT m…

ClassificationDocument Classification

On the Prunability of Attention Heads in Multilingual BERT

2021-09-26 · Aakriti Budhraja, Madhura Pande, Pratyush Kumar, Mitesh M. Khapra

Large multilingual models, such as mBERT, have shown promise in crosslingual transfer. In this work, we employ pruning to quantify the robustness and interpret layer-wise importance of mBERT. On four GLUE tasks, the rela…

L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi

2022-11-21 · Ananya Joshi, Aditi Kajale, Janhavi Gadre, Samruddhi Deode 외

Sentence representation from vanilla BERT models does not work well on sentence similarity tasks. Sentence-BERT models specifically trained on STS or NLI datasets are shown to provide state-of-the-art performance. Howeve…

BenchmarkingMachine TranslationSentenceSentence Embedding+6