Author name cluster

Xin Sheng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2022 Conference Paper

Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation

Jiquan Li
Junliang Guo
Yongxin Zhu
Xin Sheng
Deqiang Jiang
Bo Ren
Linli Xu

The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years. While one of the key principles of GEC is to keep the correct parts unchanged and avoid over-correction, previous sequence-tosequence (seq2seq) models generate results from scratch, which are not guaranteed to follow the original sentence structure and may suffer from the over-correction problem. In the meantime, the recently proposed sequence tagging models can overcome the over-correction problem by only generating edit operations, but are conditioned on human designed language-specific tagging labels. In this paper, we combine the pros and alleviate the cons of both models by proposing a novel Sequence-to-Action (S2A) module. The S2A module jointly takes the source and target sentences as input, and is able to automatically generate a token-level action sequence before predicting each token, where each action is generated from three choices named SKIP, COPY and GENerate. Then the actions are fused with the basic seq2seq framework to provide final predictions. We conduct experiments on the benchmark datasets of both English and Chinese GEC tasks. Our model consistently outperforms the seq2seq baselines, while being able to significantly alleviate the over-correction problem as well as holding better generality and diversity in the generation results compared to the sequence tagging models.

PDF Details

AAAI Conference 2020 Conference Paper

IntroVNMT: An Introspective Model for Variational Neural Machine Translation

Xin Sheng
Linli Xu
Junliang Guo
Jingchang Liu
Ruoyu Zhao
Yinlong Xu

We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. Different from the vanilla variational NMT model, IntroVNMT is capable of improving itself introspectively by evaluating the quality of the generated target sentences according to the high-level latent variables of the real and generated target sentences. As a consequence of introspective training, the proposed model is able to discriminate between the generated and real sentences of the target language via the latent variables generated by the encoder of the model. In this way, IntroVNMT is able to generate more realistic target sentences in practice. In the meantime, IntroVNMT inherits the advantages of the variational autoencoders (VAEs), and the model training process is more stable than the generative adversarial network (GAN) based models. Experimental results on different translation tasks demonstrate that the proposed model can achieve signiﬁcant improvements over the vanilla variational NMT model.

PDF Details

AAAI Conference 2019 Conference Paper

Adaptive Proximal Average Based Variance Reducing Stochastic Methods for Optimization with Composite Regularization

Jingchang Liu
Linli Xu
Junliang Guo
Xin Sheng

We focus on empirical risk minimization with a composite regulariser, which has been widely applied in various machine learning tasks to introduce important structural information regarding the problem or data. In general, it is challenging to calculate the proximal operator with the composite regulariser. Recently, proximal average (PA) which involves a feasible proximal operator calculation is proposed to approximate composite regularisers. Augmented with the prevailing variance reducing (VR) stochastic methods (e. g. SVRG, SAGA), PA based algorithms would achieve a better performance. However, existing works require a fixed stepsize, which needs to be rather small to ensure that the PA approximation is sufficiently accurate. In the meantime, the smaller stepsize would incur many more iterations for convergence. In this paper, we propose two fast PA based VR stochastic methods – APA-SVRG and APA-SAGA. By initializing the stepsize with a much larger value and adaptively decreasing it, both of the proposed methods are proved to enjoy the O(n log 1 + m0 1 ) iteration complexity to achieve the accurate solutions, where m0 is the initial number of inner iterations and n is the number of samples. Moreover, experimental results demonstrate the superiority of the proposed algorithms.

PDF Details