{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T07:38:36Z","timestamp":1723016316144},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under-translation. To alleviate these issues, we propose a synchronous bidirectional sequence generation (SBSG) model which predicts its outputs from both sides to the middle simultaneously. In the SBSG model, we enable the left-to-right (L2R) and right-to-left (R2L) generation to help and interact with each other by leveraging interactive bidirectional attention network. Experiments on neural machine translation (En-De, Ch-En, and En-Ro) and text summarization tasks show that the proposed model significantly speeds up decoding while improving the generation quality compared to the autoregressive Transformer.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/760","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"5471-5477","source":"Crossref","is-referenced-by-count":8,"title":["Sequence Generation: From Both Sides to the Middle"],"prefix":"10.24963","author":[{"given":"Long","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"},{"name":"National Laboratory of Pattern Recognition, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"},{"name":"National Laboratory of Pattern Recognition, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"},{"name":"National Laboratory of Pattern Recognition, CASIA, Beijing, China"},{"name":"CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Yu","sequence":"additional","affiliation":[{"name":"Machine Intelligence Technology Lab, Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2019","name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","start":{"date-parts":[[2019,8,10]]},"theme":"Artificial Intelligence","location":"Macao, China","end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:51:38Z","timestamp":1564300298000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/760"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/760","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}