Join the channel membership: https://www.youtube.com/c/AIPursuit/join Subscribe to the channel: https://www.youtube.com/c/AIPursuit?sub_confirmation=1 Support and Donation: Paypal ⇢ https://paypal.me/tayhengee Patreon ⇢ https://www.patreon.com/hengee BTC ⇢ bc1q2r7eymlf20576alvcmryn28tgrvxqw5r30cmpu ETH ⇢ 0x58c4bD4244686F3b4e636EfeBD159258A5513744 Doge ⇢ DSGNbzuS1s6x81ZSbSHHV5uGDxJXePeyKy Earn up to $170 welcome bonus on Huobi now with my crypto affiliate link: Binance ⇢ https://accounts.binance.com/en/register?ref=27700065 Huobi ⇢ https://www.huobi.com/en-us/topic/welcome-bonus/?invite_code=xj9pc The video is reposted for educational purposes and encourages involvement in the field of research. Source: https://parameterfree.com/icml-tutorial/ ... https://www.youtube.com/watch?v=YGEdhj1TbxI

If you would like to support the channel, please join the membership: https://www.youtube.com/c/AIPursuit/join Subscribe to the channel: https://www.youtube.com/c/AIPursuit?sub_confirmation=1 The video is reposted for educational purposes and encourages involvement in the field of AI research. Source: https://aclanthology.org/2022.acl-long.1.mp4 Abstract Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a novel approach for reducing the computational cost of BERT with minimal loss in downstream performance. Our method dynamically eliminates less contributing tokens through layers, resulting in shorter lengths and consequently lower computational cost. To determine the importance of each token representation, we train a Contribution Predictor for each layer using a gradient-based saliency method. Our experiments on several diverse classification tasks show speedups up to 22x during inference time without much sacrifice in performance. We also validate the quality of the selected tokens in our method using human annotations in the ERASER benchmark. In comparison to other widely used strategies for selecting important tokens, such as saliency and attention, our proposed method has a significantly lower false positive rate in generating rationales. Our code is freely available at https://github.com/amodaresi/AdapLeR. @inproceedings{modarressi-etal-2022-adapler, title = "{A}dap{L}e{R}: Speeding up Inference by Adaptive Length Reduction", author = "Modarressi, Ali and Mohebbi, Hosein and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.acl-long.1", doi = "10.18653/v1/2022.acl-long.1", pages = "1--15", abstract = "Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a novel approach for reducing the computational cost of BERT with minimal loss in downstream performance. Our method dynamically eliminates less contributing tokens through layers, resulting in shorter lengths and consequently lower computational cost. To determine the importance of each token representation, we train a Contribution Predictor for each layer using a gradient-based saliency method. Our experiments on several diverse classification tasks show speedups up to 22x during inference time without much sacrifice in performance. We also validate the quality of the selected tokens in our method using human annotations in the ERASER benchmark. In comparison to other widely used strategies for selecting important tokens, such as saliency and attention, our proposed method has a significantly lower false positive rate in generating rationales. Our code is freely available at https://github.com/amodaresi/AdapLeR.", } ... https://www.youtube.com/watch?v=-Dv0BZ4rXEA