paper-with-me

Papers

Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models

2024-02-16 · Minghan Wang, Thuy-Trang Vu, Yuxia Wang, Ehsan Shareghi, Gholamreza Haffari

Simultaneous machine translation (SimulMT) presents a challenging trade-off between translation quality and latency. Recent studies have shown that LLMs can achieve good performance in SimulMT tasks. However, this often comes at the expense of high inference cost and latency. In this paper, we propose a conversational SimulMT framework to enhance the inference efficiency of LLM-based SimulMT through multi-turn-dialogue-based decoding. Our experiments with Llama2-7b-chat on two SimulMT benchmarks demonstrate the superiority of LLM in translation quality while achieving comparable computational latency to specialized SimulMT models.

📄 PDF Abstract BibTeX arXiv:2402.10552

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models

2023-12-07 · Victor Agostinelli, Max Wild, Matthew Raffel, Kazi Ahmed Asif Fuad 외

Large language models (LLMs) with billions of parameters and pretrained on massive amounts of data are now capable of near or better than state-of-the-art performance in a variety of downstream natural language processin…

Machine TranslationNMTTranslation

Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation

2023-03-02 · Mengge Liu, Wen Zhang, Xiang Li, Jian Luan 외

Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. However, the general full-sentence transla…

Machine TranslationSentenceTranslation

Anticipation-free Training for Simultaneous Translation

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Simultaneous translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference between l…

HallucinationSentenceTranslation

Anticipation-Free Training for Simultaneous Machine Translation

2022-01-30 · IWSLT (ACL) 2022 5 · Chih-Chiang Chang, Shun-Po Chuang, Hung-Yi Lee

Simultaneous machine translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference b…

HallucinationMachine TranslationSentenceTranslation

Simultaneous Machine Translation with Large Language Models

2023-09-13 · Minghan Wang, Jinming Zhao, Thuy-Trang Vu, Fatemeh Shiri 외

Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long context…

Machine TranslationTranslation