English
Related papers

Related papers: BERT-EMD: Many-to-Many Layer Mapping for BERT Comp…

200 papers

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary,…

Computation and Language · Computer Science 2019-04-17 Masahiro Kaneko , Mamoru Komachi

We propose BERMo, an architectural modification to BERT, which makes predictions based on a hierarchy of surface, syntactic and semantic language features. We use linear combination scheme proposed in Embeddings from Language Models (ELMo)…

Computation and Language · Computer Science 2021-11-01 Sangamesh Kodge , Kaushik Roy

Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge devices. In this paper, we have a critical insight that…

Computation and Language · Computer Science 2021-09-17 Chenhe Dong , Guangrun Wang , Hang Xu , Jiefeng Peng , Xiaozhe Ren , Xiaodan Liang

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach…

Computation and Language · Computer Science 2021-05-26 Deming Ye , Yankai Lin , Yufei Huang , Maosong Sun

This work focuses on the efficiency of the knowledge distillation approach in generating a lightweight yet powerful BERT based model for natural language processing applications. After the model creation, we applied the resulting model,…

Computation and Language · Computer Science 2024-11-04 Ahmed Akib Jawad Karim , Kazi Hafiz Md. Asad , Md. Golam Rabiul Alam

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate…

Databases · Computer Science 2026-02-06 Alexandros Zeakis , George Papadakis , Dimitrios Skoutas , Manolis Koubarakis

Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow.…

Computation and Language · Computer Science 2019-10-21 Ze Yang , Linjun Shou , Ming Gong , Wutao Lin , Daxin Jiang

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

Computation and Language · Computer Science 2021-05-28 Fusheng Wang , Jianhao Yan , Fandong Meng , Jie Zhou

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Usma Niyaz , Deepti R. Bathula

Knowledge Distillation (KD) has emerged as a powerful technique for model compression, enabling lightweight student networks to benefit from the performance of redundant teacher networks. However, the inherent capacity gap often limits the…

Machine Learning · Computer Science 2026-02-12 Yiyun Zhou , Jingwei Shi , Mingjing Xu , Zhonghua Jiang , Jingyuan Chen

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains…

Computation and Language · Computer Science 2020-03-03 Victor Sanh , Lysandre Debut , Julien Chaumond , Thomas Wolf

Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…

Computation and Language · Computer Science 2023-05-18 Siyue Wu , Hongzhan Chen , Xiaojun Quan , Qifan Wang , Rui Wang

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

Computation and Language · Computer Science 2022-09-28 Arnav Ladkat , Aamir Miyajiwala , Samiksha Jagadale , Rekha Kulkarni , Raviraj Joshi

Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result,…

Computation and Language · Computer Science 2026-05-05 Pham Khanh Chi , Quoc Phong Dao , Thuat Nguyen , Linh Ngo Van , Trung Le , Thanh Hong Nguyen

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers.…

Computation and Language · Computer Science 2023-07-17 Qian Chen , Wen Wang , Qinglin Zhang , Chong Deng , Ma Yukun , Siqi Zheng

Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Lu Yu , Vacit Oguz Yazici , Xialei Liu , Joost van de Weijer , Yongmei Cheng , Arnau Ramisa

BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to…

Computation and Language · Computer Science 2020-11-03 Kaitao Song , Xu Tan , Tao Qin , Jianfeng Lu , Tie-Yan Liu

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this article, we probe BERT specifically to understand and measure the relational…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Machine Learning · Computer Science 2020-06-11 Benjamin Ghaemmaghami , Zihao Deng , Benjamin Cho , Leo Orshansky , Ashish Kumar Singh , Mattan Erez , Michael Orshansky