7 papers
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
Shoutao Guo, Shaolei Zhang, Zhengrui Ma +2
Simultaneous Machine Translation (SiMT) generates target translations while reading the source sentence. It relies on a policy to determine the optimal timing for reading sentences…
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Qingkai Fang, Zhengrui Ma, Yan Zhou +2
Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but it often faces the challenge of slow decoding due to the considerable length of speech s…
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
Qingkai Fang, Shaolei Zhang, Zhengrui Ma +2
Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end…
Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
Yan Gao, Zhiwei Cao, Zhongjian Miao +4
To achieve non-parametric NMT domain adaptation, -Nearest-Neighbor Machine Translation (NN-MT) constructs an external datastore to store domain-specific translation knowledge…
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Shaolei Zhang, Qingkai Fang, Shoutao Guo +3
Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real…
LLM-enhanced Self-training for Cross-domain Constituency Parsing
Jianling Li, Meishan Zhang, Peiming Guo +2
Self-training has proven to be an effective approach for cross-domain tasks, and in this study, we explore its application to cross-domain constituency parsing. Traditional self-tr…