Xiaoming Zhang


Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation
Bo Zhang | Xiaoming Zhang | Yun Liu | Lei Cheng | Zhoujun Li
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Unsupervised Domain Adaptation (UDA) aims to transfer the knowledge of source domain to the unlabeled target domain. Existing methods typically require to learn to adapt the target model by exploiting the source data and sharing the network architecture across domains. However, this pipeline makes the source data risky and is inflexible for deploying the target model. This paper tackles a novel setting where only a trained source model is available and different network architectures can be adapted for target domain in terms of deployment environments. We propose a generic framework named Cross-domain Knowledge Distillation (CdKD) without needing any source data. CdKD matches the joint distributions between a trained source model and a set of target data during distilling the knowledge from the source model to the target domain. As a type of important knowledge in the source domain, for the first time, the gradient information is exploited to boost the transfer performance. Experiments on cross-domain text classification demonstrate that CdKD achieves superior performance, which verifies the effectiveness in this novel setting.


Hierarchy Response Learning for Neural Conversation Generation
Bo Zhang | Xiaoming Zhang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

The neural encoder-decoder models have shown great promise in neural conversation generation. However, they cannot perceive and express the intention effectively, and hence often generate dull and generic responses. Unlike past work that has focused on diversifying the output at word-level or discourse-level with a flat model to alleviate this problem, we propose a hierarchical generation model to capture the different levels of diversity using the conditional variational autoencoders. Specifically, a hierarchical response generation (HRG) framework is proposed to capture the conversation intention in a natural and coherent way. It has two modules, namely, an expression reconstruction model to capture the hierarchical correlation between expression and intention, and an expression attention model to effectively combine the expressions with contents. Finally, the training procedure of HRG is improved by introducing reconstruction loss. Experiment results show that our model can generate the responses with more appropriate content and expression.


Keyphrase Generation with Correlation Constraints
Jun Chen | Xiaoming Zhang | Yu Wu | Zhao Yan | Zhoujun Li
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper, we study automatic keyphrase generation. Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues. To solve these problems, we propose a new sequence-to-sequence architecture for keyphrase generation named CorrRNN, which captures correlation among multiple keyphrases in two ways. First, we employ a coverage vector to indicate whether the word in the source document has been summarized by previous phrases to improve the coverage for keyphrases. Second, preceding phrases are taken into account to eliminate duplicate phrases and improve result coherence. Experiment results show that our model significantly outperforms the state-of-the-art method on benchmark datasets in terms of both accuracy and diversity.


Chinese Answer Extraction Based on POS Tree and Genetic Algorithm
Shuihua Li | Xiaoming Zhang | Zhoujun Li
Proceedings of the 9th SIGHAN Workshop on Chinese Language Processing

Answer extraction is the most important part of a chinese web-based question answering system. In order to enhance the robustness and adaptability of answer extraction to new domains and eliminate the influence of the incomplete and noisy search snippets, we propose two new answer exraction methods. We utilize text patterns to generate Part-of-Speech (POS) patterns. In addition, a method is proposed to construct a POS tree by using these POS patterns. The POS tree is useful to candidate answer extraction of web-based question answering. To retrieve a efficient POS tree, the similarities between questions are used to select the question-answer pairs whose questions are similar to the unanswered question. Then, the POS tree is improved based on these question-answer pairs. In order to rank these candidate answers, the weights of the leaf nodes of the POS tree are calculated using a heuristic method. Moreover, the Genetic Algorithm (GA) is used to train the weights. The experimental results of 10-fold crossvalidation show that the weighted POS tree trained by GA can improve the accuracy of answer extraction.


A Semi-Supervised Bayesian Network Model for Microblog Topic Classification
Yan Chen | Zhoujun Li | Liqiang Nie | Xia Hu | Xiangyu Wang | Tat-Seng Chua | Xiaoming Zhang
Proceedings of COLING 2012