Publications

(2021). Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021 (to appear).

(2021). Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021 (to appear).

arXiv Code

(2021). A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, NAACL 2021 (to appear).

Code

(2021). Towards Semantics-Enhanced Pre-Training: Can Lexicon Definitions Help Learning Sentence Meanings?. The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021 (to appear).

URL Code

(2021). Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation. The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021 (to appear).

arXiv

(2021). Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption. The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021 (to appear).

URL arXiv

(2021). Collaborative Group Learning. The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021 (to appear).

arXiv

(2020). Prophet Attention: Predicting Attention with Future Attention for Improved Image Captioning. Advances in Neural Information Processing Systems 33, NeurIPS 2020 (to appear).

URL

(2020). Regularizing Dialogue Generation by Imitating Implicit Scenarios. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020.

URL DOI arXiv

(2019). Exploring and Distilling Cross-Modal Information for Image Captioning. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019.

URL DOI

(2019). A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Volume 1: Long Papers.

URL DOI arXiv Code

(2018). simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018.

URL DOI arXiv Code

(2018). Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018.

URL DOI arXiv Code

(2018). A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018.

URL DOI arXiv Code

(2018). Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?. Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018.

URL arXiv Code

(2018). Deconvolution-Based Global Decoding for Neural Machine Translation. Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018.

URL arXiv Code

(2018). Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018.

URL DOI arXiv Code

(2018). A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018.

URL DOI arXiv Code

(2018). Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, Volume 1 (Long Papers).

URL DOI arXiv Code

(2018). Building an Ellipsis-Aware Chinese Dependency Treebank for Web Text. Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018.

URL arXiv Dataset

(2017). meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting. Proceedings of the 34th International Conference on Machine Learning, ICML 2017.

URL arXiv Code