{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:42:46Z","timestamp":1773931366206,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872231"],"award-info":[{"award-number":["61872231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701297"],"award-info":[{"award-number":["61701297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2993875","type":"journal-article","created":{"date-parts":[[2020,5,11]],"date-time":"2020-05-11T19:35:08Z","timestamp":1589225708000},"page":"90410-90419","source":"Crossref","is-referenced-by-count":19,"title":["Multi-Layer Transformer Aggregation Encoder for Answer Generation"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1948-2305","authenticated-orcid":false,"given":"Shengjie","family":"Shang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-698X","authenticated-orcid":false,"given":"Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihe","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1028"},{"key":"ref38","article-title":"Learning recurrent span representations for extractive question answering","author":"lee","year":"2016","journal-title":"arXiv 1611 01436"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref32","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","article-title":"The goldilocks principle: Reading Children’s books with explicit memory representations","author":"hill","year":"2015","journal-title":"arXiv 1511 02301"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"ref37","article-title":"Exploring question understanding and adaptation in neural-network-based question answering","author":"zhang","year":"2017","journal-title":"arXiv 1703 04617"},{"key":"ref36","article-title":"FastQA: A simple and efficient neural architecture for question answering","author":"weissenborn","year":"2017","journal-title":"arXiv 1703 04816"},{"key":"ref35","article-title":"End-to-end answer chunk extraction and ranking for reading comprehension","author":"yu","year":"2016","journal-title":"arXiv 1610 09996"},{"key":"ref34","article-title":"Multi-perspective context matching for machine comprehension","author":"wang","year":"2016","journal-title":"arXiv 1612 04211"},{"key":"ref10","article-title":"Bidirectional attention flow for machine comprehension","author":"seo","year":"2016","journal-title":"arXiv 1611 01603"},{"key":"ref40","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1168"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-018-3181-2"},{"key":"ref14","article-title":"R3: Reinforced reader-ranker for open-domain question answering","author":"wang","year":"2017","journal-title":"arXiv 1709 00023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1096"},{"key":"ref16","article-title":"Dependent gated reading for cloze-style question answering","author":"ghaeini","year":"2018","journal-title":"arXiv 1805 10528"},{"key":"ref17","article-title":"A heterogeneous graph with factual, temporal and logical knowledge for question answering over dynamic contexts","author":"zhong","year":"2020","journal-title":"arXiv 2004 12057"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-019-01344-9"},{"key":"ref27","first-page":"193","article-title":"MCTest: A challenge dataset for the open-domain machine comprehension of text","author":"richardson","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref6","article-title":"LSTM-based deep learning models for non-factoid answer selection","author":"tan","year":"2015","journal-title":"arXiv 1511 04108"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v37i1.2636"},{"key":"ref5","article-title":"Deep learning for answer sentence selection","author":"yu","year":"2014","journal-title":"arXiv 1412 1632 [cs]"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/STARTUP.2016.7583963"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"4295","DOI":"10.1007\/s00500-017-2852-8","article-title":"Multiple relations extraction among multiple entities in unstructured text","volume":"22","author":"liu","year":"2018","journal-title":"Soft Comput"},{"key":"ref2","article-title":"QANet: Combining local convolution with global self-attention for reading comprehension","author":"yu","year":"2018","journal-title":"arXiv 1804 09541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2116"},{"key":"ref1","article-title":"Machine comprehension using match-LSTM and answer pointer","author":"wang","year":"2016","journal-title":"arXiv 1608 07905"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.07.082"},{"key":"ref21","article-title":"Lightweight convolutional approaches to reading comprehension on SQuAD","author":"bell","year":"2018","journal-title":"arXiv 1810 08680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1026"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220048"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1166"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09091180.pdf?arnumber=9091180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T10:53:29Z","timestamp":1643280809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9091180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2993875","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}