no code implementations • COLING 2022 • Yong Wang, Xinwei Geng
Non-autoregressive translation (NAT) models, which eliminate the sequential dependencies within the target sentence, have achieved remarkable inference speed, but suffer from inferior translation quality.
1 code implementation • EMNLP 2021 • Xinwei Geng, Xiaocheng Feng, Bing Qin
Towards keeping the consistency of data distribution with iterative decoding, an iterative training strategy is employed to further improve the capacity of rewriting.
1 code implementation • 25 May 2023 • Yichong Huang, Xiaocheng Feng, Xinwei Geng, Baohang Li, Bing Qin
Multilingual neural machine translation has witnessed remarkable progress in recent years.
1 code implementation • 3 May 2022 • Yichong Huang, Xiaocheng Feng, Xinwei Geng, Bing Qin
In this paper, we propose a novel training strategy named LSSD (Language-Specific Self-Distillation), which can alleviate the convergence inconsistency and help MNMT models achieve the best performance on each language pair simultaneously.
1 code implementation • 7 Dec 2020 • Xiachong Feng, Xiaocheng Feng, Bing Qin, Xinwei Geng
First, we present a Dialogue Discourse-Dware Meeting Summarizer (DDAMS) to explicitly model the interaction between utterances in a meeting by modeling different discourse relations.
1 code implementation • ACL 2020 • Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words.
no code implementations • 26 Dec 2018 • Xinwei Geng, Long-Yue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu
Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process.
no code implementations • EMNLP 2018 • Xinwei Geng, Xiaocheng Feng, Bing Qin, Ting Liu
Although end-to-end neural machine translation (NMT) has achieved remarkable progress in the recent years, the idea of adopting multi-pass decoding mechanism into conventional NMT is not well explored.
no code implementations • 18 Dec 2015 • Bing Qin, Duyu Tang, Xinwei Geng, Dandan Ning, Jiahao Liu, Ting Liu
Generating an article automatically with computer program is a challenging task in artificial intelligence and natural language processing.