Multi-Pass Transformer for Machine Translation
원문 초록
In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. To maintain a directed acyclic graph structure, the encoder stack of a transformer is repeated along a new multi-pass dimension, keeping the parameters tied, and information is allowed to proceed unidirectionally both towards deeper layers within an encoder stack and towards any layer of subsequent stacks. We consider both soft (i.e., continuous) and hard (i.e., discrete) connections between parallel encoder stacks, relying on a neural architecture search to find the best connection pattern in the hard case. We perform an extensive ablation study of the proposed MPT architecture and compare it with other state-of-the-art transformer architectures. Surprisingly, Base Transformer equipped with MPT can surpass the performance of Large Transformer on the challenging machine translation En-De and En-Fr datasets. In the hard connection case, the optimal connection pattern found for En-De also leads to improved performance for En-Fr.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
Gender Bias in English-to-Greek Machine Translation
TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translations
단순할수록 좋을 때: 중세 라틴어 필사본을 위한 번역 파이프라인 평가
When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts
CoPiT: 전통 문자 기반 이중 문자 체계 저자원 몽골어를 위한 인지적 피벗 번역
CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script
토론
이 논문과 연결된 포럼 글이 아직 없습니다.