1. <nav id="jhvnf"></nav>

      <listing id="jhvnf"></listing>

      1. <output id="jhvnf"></output>
            1. <code id="jhvnf"></code>
              1. <var id="jhvnf"><object id="jhvnf"><noscript id="jhvnf"></noscript></object></var>

                1. <nav id="jhvnf"></nav>
                  <listing id="jhvnf"></listing>
                      1. <small id="jhvnf"></small><dd id="jhvnf"><delect id="jhvnf"></delect></dd>
                            1. <span id="jhvnf"></span>

                              自然语言处理与信息检索共享平台 自然语言处理与信息检索共享平台

                              Pay Less Attention with Lightweight and Dynamic Convolutions

                              NLPIR SEMINAR Y2019#10

                              INTRO

                              In the new semester, our Lab, Web Search Mining and Security Lab, plans to hold an academic seminar every Monday, and each time a keynote speaker will share understanding of papers on his/her related research with you.

                              Arrangement

                              This week’s seminar is organized as follows:

                              1. The seminar time is 1.pm, Mon, at Zhongguancun Technology Park ,Building 5, 1306.
                              2. The lecturer is Zhaoyou Liu , the paper’s title is Pay Less Attention with Lightweight and Dynamic Convolutions.
                              3. The seminar will be hosted by Gang Wang.
                              4. Attachment is the paper of this seminar, please download in advance.

                              Everyone interested in this topic is welcomed to join us. the following is the abstract for this week’s paper.

                              Pay Less Attention with Lightweight and Dynamic Convolutions

                              FelixWu, Angela Fan, Alexei Baevski, Yann N. Dauphin, Michael Auli

                              abstract

                              Self-attention is a useful mechanism to build generative models for language and images. It determines the importance of context elements by comparing each element to the current time step. In this paper, we show that a very lightweight convolution can perform competitively to the best reported self-attention results. Next, we introduce dynamic convolutions which are simpler and more efficient than self-attention. We predict separate convolution kernels based solely on the current time-step in order to determine the importance of context elements. The number of operations required by this approach scales linearly in the input length, whereas self-attention is quadratic. Experiments on large-scale machine translation, language modeling and abstractive summarization show that dynamic convolutions improve over strong self-attention models. On the WMT’14 English-German test set dynamic convolutions achieve a new state of the art of 29.7 BLEU.

                              You May Also Like

                              About the Author: nlpvv

                              发表评论

                              十一选五投注攻略