Search Results for author: Xian Qian

Found 14 papers, 3 papers with code

SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation

1 code implementation19 Dec 2022 Wenda Xu, Xian Qian, Mingxuan Wang, Lei LI, William Yang Wang

Existing learned metrics have gaps to human judgements, are model-dependent or are limited to the domains or tasks where human ratings are available.

Dialogue Generation Machine Translation +2

The VolcTrans System for WMT22 Multilingual Machine Translation Task

no code implementations20 Oct 2022 Xian Qian, Kai Hu, Jiaqiang Wang, Yifeng Liu, Xingyuan Pan, Jun Cao, Mingxuan Wang

This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation.

Machine Translation Translation

PARAGEN : A Parallel Generation Toolkit

1 code implementation7 Oct 2022 Jiangtao Feng, Yi Zhou, Jun Zhang, Xian Qian, Liwei Wu, Zhexi Zhang, Yanming Liu, Mingxuan Wang, Lei LI, Hao Zhou

PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.

Model Selection

LightSeq2: Accelerated Training for Transformer-based Models on GPUs

1 code implementation12 Oct 2021 Xiaohui Wang, Yang Wei, Ying Xiong, Guyue Huang, Xian Qian, Yufei Ding, Mingxuan Wang, Lei LI

In this paper, we present LightSeq2, a system to accelerate training for a general family of Transformer models on GPUs.

Machine Translation Speech Recognition +1

A non-DNN Feature Engineering Approach to Dependency Parsing -- FBAML at CoNLL 2017 Shared Task

no code implementations CONLL 2017 Xian Qian, Yang Liu

For this year{'}s multilingual dependency parsing shared task, we developed a pipeline system, which uses a variety of features for each of its components.

Dependency Parsing Feature Engineering +4

2-Slave Dual Decomposition for Generalized Higher Order CRFs

no code implementations TACL 2014 Xian Qian, Yang Liu

We show that the decoding problem in generalized Higher Order Conditional Random Fields (CRFs) can be decomposed into two parts: one is a tree labeling problem that can be solved in linear time using dynamic programming; the other is a supermodular quadratic pseudo-Boolean maximization problem, which can be solved in cubic time using a minimum cut algorithm.

named-entity-recognition Named Entity Recognition +2

Branch and Bound Algorithm for Dependency Parsing with Non-local Features

no code implementations TACL 2013 Xian Qian, Yang Liu

Graph based dependency parsing is inefficient when handling non-local features due to high computational complexity of inference.

Dependency Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.