activity
20182022
most citedMultilingual Neural Machine Translation With Soft Decoupled Encoding

43 citations · 47 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2022

A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models

Jimin Sun, Patrick Fernandes, Xinyi Wang +1

Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue e…

cs.CL2022

Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation

Xinyi Wang, Sebastian Ruder, Graham Neubig

The performance of multilingual pretrained models is highly dependent on the availability of monolingual or parallel text present in a target language. Thus, the majority of the wo…

cs.CL20194 cited

Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation

Xinyi Wang, Graham Neubig

To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all…

cs.CL2019

compare-mt: A Tool for Holistic Comparison of Language Generation Systems

Graham Neubig, Zi-Yi Dou, Junjie Hu +4

In this paper, we describe compare-mt, a tool for holistic analysis and comparison of the results of systems for language generation tasks such as machine translation. The main goa…

cs.CL201943 cited

Multilingual Neural Machine Translation With Soft Decoupled Encoding

Xinyi Wang, Hieu Pham, Philip Arthur +1

Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challe…

cs.CL2018

A Tree-based Decoder for Neural Machine Translation

Xinyi Wang, Hieu Pham, Pengcheng Yin +1

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes…