Ranknas: Efficient neural architecture search by pairwise ranking
This paper addresses the efficiency challenge of Neural Architecture Search (NAS) by
formulating the task as a ranking problem. Previous methods require numerous training …
formulating the task as a ranking problem. Previous methods require numerous training …
Hybrid-regressive neural machine translation
In this work, we empirically confirm that non-autoregressive translation with an iterative
refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is …
refinement mechanism (IR-NAT) suffers from poor acceleration robustness because it is …
The NiuTrans System for the WMT21 Efficiency Task
This paper describes the NiuTrans system for the WMT21 translation efficiency task
(http://statmt. org/wmt21/efficiency-task. html). Following last year's work, we explore various …
(http://statmt. org/wmt21/efficiency-task. html). Following last year's work, we explore various …
特許機械翻訳の課題解決に向けた機械翻訳技術解説
今村賢治， 越前谷博， 江原暉将， 後藤功雄， 須藤克仁… - 自然言語処理, 2022 - jstage.jst.go.jp
抄録 本解説論文では, 特許を対象とした機械翻訳における種々の課題に対する関連技術の解説を
行う. 特許に対する機械翻訳は実用的にも学術的にも長い歴史を持つが, ニューラル機械翻訳の …
行う. 特許に対する機械翻訳は実用的にも学術的にも長い歴史を持つが, ニューラル機械翻訳の …