Xiaomian Kang — accepted AI-conference papers

2025

Investigating Hallucinations in Simultaneous Machine Translation: Knowledge Distillation Solution and Components Analysis

Donglei Yu, Xiaomian Kang, Yuchen Liu, Feifei Zhai, Nanchang Cheng, Yu Zhou +1

NAACL 2025long

Simultaneous Machine Translation (SiMT) generates target translation before receiving the whole source sentence and faces a serious hallucination problem. In contrast, traditional offline machine translation (OMT) models exhibit significantly fewer hallucinations. Motivated by this disparity, we pro…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Self-Modifying State Modeling for Simultaneous Machine Translation

Donglei Yu, Xiaomian Kang, Yuchen Liu, Yu Zhou, Chengqing Zong

ACL 2024long

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a decision path. Existing SiMT methods, which learn the poli…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗