English
Related papers

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

200 papers

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Information Retrieval · Computer Science 2020-02-18 Wenhao Lu , Jian Jiao , Ruofei Zhang

Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-18 Jinle Zeng , Min Li , Zhihua Wu , Jiaqi Liu , Yuang Liu , Dianhai Yu , Yanjun Ma

The Earth mover's distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent.…

Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of…

Computation and Language · Computer Science 2021-06-17 Xinyi Wang , Haiqin Yang , Liang Zhao , Yang Mo , Jianping Shen

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

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

Pre-trained Language Models (PLMs) have been widely used in various natural language processing (NLP) tasks, owing to their powerful text representations trained on large-scale corpora. In this paper, we propose a new PLM called PERT for…

Computation and Language · Computer Science 2022-03-15 Yiming Cui , Ziqing Yang , Ting Liu

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable for tasks like…

Computation and Language · Computer Science 2020-05-19 Pengcheng Yin , Graham Neubig , Wen-tau Yih , Sebastian Riedel

Pre-trained language models such as BERT have become a more common choice of natural language processing (NLP) tasks. Research in word representation shows that isotropic embeddings can significantly improve performance on downstream tasks.…

Computation and Language · Computer Science 2021-08-30 Yuxin Liang , Rui Cao , Jie Zheng , Jie Ren , Ling Gao

Word-embeddings are vital components of Natural Language Processing (NLP) models and have been extensively explored. However, they consume a lot of memory which poses a challenge for edge deployment. Embedding matrices, typically, contain…

Computation and Language · Computer Science 2020-11-12 Vasileios Lioutas , Ahmad Rashid , Krtin Kumar , Md Akmal Haidar , Mehdi Rezagholizadeh

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Computation and Language · Computer Science 2020-04-21 Anne Lauscher , Ivan Vulić , Edoardo Maria Ponti , Anna Korhonen , Goran Glavaš

Large-scale pre-trained sequence-to-sequence models like BART and T5 achieve state-of-the-art performance on many generative NLP tasks. However, such models pose a great challenge in resource-constrained scenarios owing to their large…

Computation and Language · Computer Science 2022-03-23 Zheng Li , Zijian Wang , Ming Tan , Ramesh Nallapati , Parminder Bhatia , Andrew Arnold , Bing Xiang , Dan Roth

Knowledge Distillation (KD) is a predominant approach for BERT compression. Previous KD-based methods focus on designing extra alignment losses for the student model to mimic the behavior of the teacher model. These methods transfer the…

Computation and Language · Computer Science 2024-03-21 Taiqiang Wu , Cheng Hou , Shanshan Lao , Jiayi Li , Ngai Wong , Zhe Zhao , Yujiu Yang

Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during…

Machine Learning · Statistics 2018-06-15 Yoonho Lee , Seungjin Choi

With the explosive growth of biomedical literature, designing automatic tools to extract information from the literature has great significance in biomedical research. Recently, transformer-based BERT models adapted to the biomedical domain…

Computation and Language · Computer Science 2020-11-03 Peng Su , K. Vijay-Shanker

Retrieval and ranking models are the backbone of many applications such as web search, open domain QA, or text-based recommender systems. The latency of neural ranking models at query time is largely dependent on the architecture and…

Information Retrieval · Computer Science 2021-01-25 Sebastian Hofstätter , Sophia Althammer , Michael Schröder , Mete Sertkan , Allan Hanbury

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Computation and Language · Computer Science 2023-05-25 Linhan Zhang , Qian Chen , Wen Wang , Chong Deng , Xin Cao , Kongzhang Hao , Yuxin Jiang , Wei Wang

Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT), yet they suffer from high computational cost and latency. Therefore, transferring translation knowledge from giant LLMs to…

Computation and Language · Computer Science 2024-04-02 Jiahuan Li , Shanbo Cheng , Shujian Huang , Jiajun Chen

Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a…

Computation and Language · Computer Science 2017-08-09 Markus Freitag , Yaser Al-Onaizan , Baskaran Sankaran

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-20 Ji Won Yoon , Hyeonseung Lee , Hyung Yong Kim , Won Ik Cho , Nam Soo Kim

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut