Selected Publications:

[ 2024 | 2023 | 2022 | 2021 | 2020 | 2019 | 2018 | 2017 | 2016 | 2015 | 2014 | 2013 | 2012 | 2011 | 2010 | 2009 | 2008 | 2007 and Prior ]

2024

  • Jie Ruan, Wenqing Wang and Xiaojun Wan. Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation. NAACL 2024. (Long Paper)

  • Huixuan Zhang and Xiaojun Wan. Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection. LREC-COLING 2024. (Long Paper)

  • Xiao Pu, Mingqi Gao and Xiaojun Wan. Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks. LREC-COLING 2024. (Long Paper)

  • Xunjian Yin, Xinyu Hu, Jin Jiang and Xiaojun Wan. Error-Robust Retrieval for Chinese Spelling Check. LREC-COLING 2024. (Long Paper)

  • Jin Jiang, Xunjian Yin, Xiaojun Wan, Wei Peng, Rongjun Li, Jingyuan Yang and Yanquan Zhou. Contextual Modeling for Document-level ASR Error Correction. LREC-COLING 2024. (Long Paper)

  • Xunjian Yin, Jin Jiang, Liming Yang and Xiaojun Wan. History Matters: Temporal Knowledge Editing in Large Language Model. AAAI 2024.

  • Jie Ruan, Xiao Pu, Mingqi Gao, Xiaojun Wan and Yuesheng Zhu. Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling. AAAI 2024.

  • Jie Ruan, Yue Wu, Xiaojun Wan and Yuesheng Zhu. Describe Images in a Boring Way: Towards Cross-Modal Sarcasm Generation. WACV 2024.

2023

  • Hui Liu and Xiaojun Wan. Models See Hallucinations: Evaluating the Factuality in Video Captioning. EMNLP 2023. (Long Paper)

  • Xinyu Hu and Xiaojun Wan. Exploring Discourse Structure in Document-level Machine Translation. EMNLP 2023. (Long Paper)

  • Xunjian Yin, Baizhou Huang and Xiaojun Wan. ALCUNA: Large Language Models Meet New Knowledge. EMNLP 2023. (Long Paper)

  • Zhaohong Wan, Xiaojun Wan, Wei Peng and Rongjun Li. New Datasets and Controllable Iterative Data Augmentation Method for Code-switching ASR Error Correction. EMNLP 2023 (Findings). (Long Paper)

  • Shiping Yang, Renliang Sun and Xiaojun Wan. A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection. EMNLP 2023 (Findings). (Long Paper)

  • Xinyu Hu, Xunjian Yin and Xiaojun Wan. Exploring Context-Aware Evaluation Metrics for Machine Translation. EMNLP 2023 (Findings). (Short Paper)

  • Yunxiang Zhang and Xiaojun Wan. SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning. NeurIPS 2023. (Datasets and Benchmarks Track)

  • Shiping Yang, Renliang Sun and Xiaojun Wan. A New Dataset and Empirical Study for Sentence Simplification in Chinese. ACL 2023. (Long Paper)

  • Xu Zhang and Xiaojun Wan. MIL-Decoding: Detoxifying Language Models at Token-Level via Multiple Instance Learning. ACL 2023. (Long Paper)

  • Mingqi Gao, Xiaojun Wan, Jia Su, Zhefeng Wang and Baoxing Huai. Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework. ACL 2023. (Long Paper)

  • Mingqi Gao, Wenqing Wang, Xiaojun Wan and Yuemei Xu. Evaluating Factuality in Cross-lingual Summarization. ACL 2023 (Findings). (Long Paper)

  • Junzhe Zhang and Xiaojun Wan. Exploring the Impact of Vision Features in News Image Captioning. ACL 2023 (Findings). (Long Paper)

  • Renliang Sun, Wei Xu and Xiaojun Wan. Teaching the Pre-trained Model to Generate Simple Texts for Text Simplification. ACL 2023 (Findings). (Short Paper)

  • Renliang Sun, Zhixian Yang and Xiaojun Wan. Exploiting Summarization Data to Help Text Simplification. EACL 2023. (Long Paper)

  • Xinyu Hu and Xiaojun Wan. RST Discourse Parsing as Text-to-Text Generation. IEEE Transactions on Audio, Speech and Language Processing.

2022

  • Xiang Chen, Zhixian Yang and Xiaojun Wan. Relation-Constrained Decoding for Text Generation. NeurIPS 2022.

  • Zhe Lin and Xiaojun Wan. Visual Information Guided Zero-Shot Paraphrase Generation. COLING 2022. (Long Paper)

  • Zhixian Yang, Pengxuan Xu and Xiaojun Wan. Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling. COLING 2022. (Long Paper)

  • Sheng Xu, Xiaojun Wan, Sen Hu, Mengdi Zhou, Teng Xu, Hongbin Wang, Haitao Mi. COSSUM: Towards Conversation-Oriented Structured Summarization for Automatic Medical Insurance Assessment. KDD 2022.

  • Yunxiang Zhang and Xiaojun Wan. MOVER: Mask, Over-generate and Rank for Hyperbole Generation. NAACL 2022. (Long Paper)

  • Mingqi Gao and Xiaojun Wan. DialSummEval: Revisiting Summarization Evaluation for Dialogues. NAACL 2022. (Long Paper)

  • Zhixian Yang, Renliang Sun and Xiaojun Wan. Nearest Neighbor Knowledge Distillation for Neural Machine Translation. NAACL 2022. (Long Paper)

  • Zhixian Yang and Xiaojun Wan. Dependency-based Mixture Language Models. ACL 2022. (Long Paper)

  • Xunjian Yin and Xiaojun Wan. How Do Seq2Seq Models Perform on End-to-End Data-to-Text Generation? ACL 2022. (Long Paper)

  • Yunxiang Zhang and Xiaojun Wan. BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles. AAAI 2022.

  • Sheng Xu and Xiaojun Wan. PosterBot: A System for Generating Posters of Scientific Papers with Neural Models. AAAI 2022. (Demo Paper)

  • Sheng Xu and Xiaojun Wan. Automatic Slides Generation for Scholarly Papers: A Fine-grained Dataset and Baselines. AAAI 2022. (Student Poster Paper)

  • Ke Wang and Xiaojun Wan. Counterfactual Representation Augmentation for Cross-Domain Sentiment Analysis. IEEE Transactions on Affective Computing.

2021

  • Yitao Cai, Yue Cao and Xiaojun Wan. Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot. EMNLP 2021. (Long Paper)

  • Renliang Sun, Hanqi Jin and Xiaojun Wan. Document-Level Text Simplification: Dataset, Criteria and Baseline. EMNLP 2021. (Long Paper)

  • Chenxiao Liu and Xiaojun Wan. CodeQA: A Question Answering Dataset for Source Code Comprehension. EMNLP 2021 (Findings). (Long Paper)

  • Zhe Lin, Yitao Cai and Xiaojun Wan. Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering. EMNLP 2021 (Findings). (Long Paper)

  • Hui Liu and Xiaojun Wan. Video Paragraph Captioning as a Text Summarization Task. ACL 2021. (Short Paper)

  • Ke Wang and Xiaojun Wan. TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization. ACL 2021 (Findings). (Long Paper)

  • Yitao Cai, Zhe Lin and Xiaojun Wan. Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing. ACL 2021 (Findings). (Long Paper)

  • Zhe Lin and Xiaojun Wan. Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach. ACL 2021 (Findings). (Long Paper)

  • Xiang Chen, Yue Cao and Xiaojun Wan. WIND: Weighting Instances Differentially for Model-Agnostic Domain Adaptation. ACL 2021 (Findings). (Long Paper)

  • Xinyu Xing and Xiaojun Wan. Structure-Aware Pre-Training for Table-to-Text Generation. ACL 2021 (Findings). (Short Paper)

  • Yue Cao, Hao-Ran Wei, Boxing Chen and Xiaojun Wan. Continual Learning for Neural Machine Translation. NAACL 2021. (Long Paper)

  • Qingxiu Dong, Xiaojun Wan and Yue Cao. ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation. EACL 2021. (Full Paper)

  • Shaowei Yao, Jiwei Tan, Xi Chen, Keping Yang, Rong Xiao, Hongbo Deng and Xiaojun Wan. Learning a Product Relevance Model from Click-Through Data in e-Commerce. TheWebConf/WWW 2021. (Full Paper)

  • Zhe Lin and Xiaojun Wan. Neural Sentence Simplification with Semantic Dependency Information. AAAI 2021. (Full Paper)

  • Ke Wang, Guandan Chen, Zhongqiang Huang, Xiaojun Wan and Fei Huang. Bridging the Domain Gap: Improve Informal Language Translation via Counterfactual Domain Adaptation. AAAI 2021. (Full Paper)

  • Zi Chai and Xiaojun Wan. Adverse Drug Events Detection, Extraction and Normalization from Online Comments of Chinese Patent Medicines. PAKDD 2021.

  • Junjie Cao, Zi Lin, Weiwei Sun and Xiaojun Wan. Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing. Computational Linguistics.

2020

  • Renliang Sun, Zhe Lin and Xiaojun Wan. On the Helpfulness of Document Context to Sentence Simplification. COLING 2020. (Long Paper)

  • Zhaohong Wan,Xiaojun Wan and Wenguang Wang. Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation. COLING 2020. (Long Paper)

  • Yitao Cai and Xiaojun Wan. IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation. EMNLP 2020. (Long Paper)

  • Zhiwei Yu, Hongyu Zang and Xiaojun Wan. Routing Enforced Generative Model for Recipe Generation. EMNLP 2020. (Long Paper)

  • Zhiwei Yu, Hongyu Zang and Xiaojun Wan. Homophonic Pun Generation with Lexically Constrained Rewriting. EMNLP 2020. (Short Paper)

  • Yue Cao and Xiaojun Wan. DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network. Findings of EMNLP 2020. (Long Paper)

  • Hanqi Jin and Xiaojun Wan. Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization. Findings of EMNLP 2020. (Long Paper)

  • Ke Wang and Xiaojun Wan. Adversarial Text Generation via Sequence Contrast Discrimination. Findings of EMNLP 2020. (Short Paper)

  • Hanqi Jin, Yue Cao, Tianming Wang, Xinyu Xing and Xiaojun Wan. Recent Advances of Neural Text Generation: Core Tasks, Datasets, Models and Challenges. SCIENCE CHINA Technological Sciences. (Invited Survey)

  • Yue Cao, Hanqi Jin, Xiaojun Wan and Zhiwei Yu. Domain-Adaptive Neural Automated Essay Scoring. SIGIR 2020. (Full Paper)

  • Xinyu Xing, Xiaosheng Fan and Xiaojun Wan. Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study. ACL 2020. (Long Paper)

  • Hanqi Jin, Tianming Wang and Xiaojun Wan. Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization. ACL 2020. (Long Paper)

  • Yue Cao, Hui Liu and Xiaojun Wan. Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization. ACL 2020. (Long Paper)

  • Zi Chai and Xiaojun Wan. Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction. ACL 2020. (Long Paper)

  • Shaowei Yao, Tianming Wang and Xiaojun Wan. Heterogeneous Graph Transformer for Graph-to-Sequence Learning. ACL 2020. (Long Paper)

  • Yuanyuan Zhao, Weiwei Sun, Junjie Cao and Xiaojun Wan. Semantic Parsing for English as a Second Language. ACL 2020. (Long Paper)

  • Shaowei Yao and Xiaojun Wan. Multimodal Transformer for Multimodal Machine Translation. ACL 2020. (Short Paper)

  • Tianming Wang, Xiaojun Wan and Shaowei Yao. Better AMR-To-Text Generation with Graph Structure Reconstruction. IJCAI-PRICAI 2020.

  • Yue Cao, Xiaojun Wan, Jin-ge Yao and Dian Yu. MultiSumm: Towards a Unified Model for Multi-Lingual Abstractive Summarization. AAAI 2020.

  • Hanqi Jin, Tianming Wang and Xiaojun Wan. SemSUM: Semantic Dependency Guided Neural Abstractive Summarization. AAAI 2020.

  • Zilong Wang, Zhaohong Wan and Xiaojun Wan. TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis. TheWebConf/WWW 2020. (Short Oral Paper)

2019

  • Tianming Wang, Xiaojun Wan and Hanqi Jin. AMR-To-Text Generation with Graph Transformer. Transactions of the Association for Computational Linguistics (TACL).

  • Ke Wang, Hang Hua and Xiaojun Wan. Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation. NeurIPS 2019.

  • Yanlin Feng and Xiaojun Wan. Towards a Unified End-to-End Approach for Fully Unsupervised Cross-lingual Sentiment Analysis. CoNLL 2019.

  • Da Yin, Xiao Liu and Xiaojun Wan. Interactive Multi-grained Joint Model for Targeted Sentiment Analysis. CIKM 2019. (Full Paper)

  • Hui Liu and Xiaojun Wan. Neural Review Summarization Leveraging User and Product Information. CIKM 2019. (Short Paper)

  • Lixin Liu, Jiajun Tang, Xiaojun Wan and Zongming Guo. Generating Diverse and Descriptive Image Captions Using Visual Paraphrases. ICCV 2019.

  • Ke Wang and Xiaojun Wan. Automatic Generation of Sentimental Texts via Mixture Adversarial Networks. Artificial Intelligence (AIJ).

  • Hongyu Zang, Zhiwei Yu and Xiaojun Wan. Automated Chess Commentator Powered by Neural Chess Engine. In ACL 2019. (Long Paper)

  • Zi Chai, Xinyu Xing, Xiaojun Wan and Bo Huang. Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums. In ACL 2019. (Long Paper)

  • Yitao Cai, Huiyu Cai and Xiaojun Wan. Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model. In ACL 2019. (Long Paper)

  • Tianming Wang and Xiaojun Wan. T-CVAE: Transformer-Based Conditioned Variational Autoencoder for Story Completion. In IJCAI 2019. (Full Paper)

  • Yitao Cai and Xiaojun Wan. Multi-Domain Sentiment Classification Based on Domain-Aware Embedding and Attention. In IJCAI 2019. (Full Paper)

  • Zi Chai, Xiaojun Wan, Zhao Zhang and Minjie Li. Harvesting Drug Effectiveness from Social Media. In SIGIR 2019. (Full Paper)

  • Zhiwei Yu and Xiaojun Wan. How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation. In NAACL 2019. (Long Paper)

  • Yanlin Feng and Xiaojun Wan. Learning Bilingual Sentiment-Specific Word Embeddings without Cross-Lingual Supervision. In NAACL 2019. (Long Paper)

  • Hui Liu, Wentao Qin and Xiaojun Wan. INS: An Interactive Chinese News Synthesis System. In NAACL 2019. (Demo Paper, video)

  • Tianming Wang and Xiaojun Wan. Hierarchical Attention Networks for Sentence Ordering. In AAAI 2019. (Full Paper)

  • Zilong Wang, Zhaohong Wan and Xiaojun Wan. BAB-QA: A New Neural Model for Emotion Detection in Multi-Party Dialogue. In PAKDD 2019.

  • Minghao Chen and Xiaojun Wan. Neural Comment Generation for Source Code with Auxiliary Code Classification Task. In APSEC 2019.

  • Weiwei Sun, Yufei Chen, Xiaojun Wan and Meichun Liu. Parsing Chinese Sentences with Grammatical Relations. Computational Linguistics.

2018

  • Xiaojun Wan, Fuli Luo, Xue Sun, Songfang Huang and Jin-ge Yao. Cross-Language Document Summarization via Extraction and Ranking of Multiple Summaries. Knowledge and Information Systems (k).

  • Jiwei Tan, Xiaojun Wan, Hui Liu and Jianguo Xiao. QuoteRec: Towards Quote Recommendation for Writing. ACM Transactions on Information Systems (TOIS).

  • Ke Wang and Xiaojun Wan. Sentiment Analysis of Peer Review Texts for Scholarly Papers. In SIGIR 2018. (Full Paper)

  • Ke Wang and Xiaojun Wan. SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks. In IJCAI 2018. (Full Paper, Distinguished Paper Award, link, code)

  • Tianyu Liu, Wei Wei and Xiaojun Wan. Learning to Explain Ambiguous Headlines of Online News. In IJCAI 2018. (Full Paper)

  • Yajie Ye, Weiwei Sun and Xiaojun Wan. Language Generation via DAG Transduction. In ACL 2018. (Long Paper)

  • Zhiwei Yu, Jiwei Tan and Xiaojun Wan. A Neural Approach to Pun Generation. In ACL 2018. (Long Paper)

  • Yufei Chen, Yuanyuan Zhao, Weiwei Sun and Xiaojun Wan. Pre- and In-Parsing Models for Neural Empty Category Detection. In ACL 2018. (Long Paper)

  • Yufei Chen, Weiwei Sun and Xiaojun Wan. Accurate SHRG-Based Semantic Parsing. In ACL 2018. (Long Paper)

  • Yitao Cai, Yin Li and Xiaojun Wan. Sense-Aware Neural Models for Pun Location in Texts. In ACL 2018. (Short Paper)

  • Liunian Li and Xiaojun Wan. Point Precisely: Towards Ensuring the Precision of Data in Generated Texts Using Delayed Copy Mechanism. In COLING 2018. (Long Paper)

  • Lixin Liu, Xiaojun Wan and Zongming Guo. Images2Poem: Generating Chinese Poetry From Image Streams. In ACM Multimedia 2018. (Full Paper)

  • Zi Lin, Yuguang Duan, Yuanyuan Zhao, Weiwei Sun and Xiaojun Wan. Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and the L2-L1 Parallel Data. In EMNLP 2018. (Long Paper)

  • Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun and Xiaojun Wan. Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis. In CoNLL 2018. (Long Paper)

  • Jianmin Zhang, Jiwei Tan and Xiaojun Wan. Adapting Neural Single-Document Summarization Model for Abstractive Multi-Document Summarization: A Pilot Study. INLG 2018. (Long Paper, arXiv)

  • Xiaojun Wan. Book Review for "Automatic Text Simplification". Computational Linguistics.

2017

  • Jin-ge Yao, Xiaojun Wan and Jianguo Xiao. Recent Advances in Document Summarization. Knowledge and Information Systems (KAIS). (Survey Paper, draft)

  • Jin-ge Yao and Xiaojun Wan. Greedy Flipping for Constrained Word Deletion. In AAAI 2017. (Full Paper)

  • Sida Wang, Xiaojun Wan and Shikang Du. Phrase-Based Presentation Slides Generation for Academic Papers. In AAAI 2017. (Full Paper)

  • Fang Liu and Xiaojun Wan. ATSUM: Extracting Attractive Summaries for News Propagation on Microblogs. In AAAI 2017. (Student Short Paper)

  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. Abstractive Document Summarization with a Graph-Based Attentional Neural Model. In ACL 2017. (Outstanding Long Paper, more details, code)

  • Junjie Cao, Sheng Huang, Weiwei Sun and Xiaojun Wan. Parsing to 1-Endpoint-Crossing, Pagenumber-2 Graphs. In ACL 2017. (Long Paper)

  • Weiwei Sun, Junjie Cao and Xiaojun Wan. Semantic Dependency Parsing via Book Embedding. In ACL 2017. (Long Paper)

  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. From Neural Sentence Summarization to Headline Generation: A Coarse-to-Fine Approach. In IJCAI 2017. (Full Paper)

  • Wei Wei and Xiaojun Wan. Learning to Identify Ambiguous and Misleading News Headlines. In IJCAI 2017. (Full Paper)

  • Weiwei Sun, Yantao Du and Xiaojun Wan. Parsing for Grammatical Relations via Graph Merging. In CoNLL 2017. (Full Paper)

  • Xun Zhang, Weiwei Sun and Xiaojun Wan. The Covert Helps Parse the Overt . In CoNLL 2017. (Full Paper)

  • Hongyu Zang and Xiaojun Wan. Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores. In INLG 2017. (Full Paper)

  • Jin-ge Yao, Jianmin Zhang, Xiaojun Wan, and Jianguo Xiao. Content Selection for Real-time Sports News Construction from Commentary Texts. In INLG 2017. (Full Paper)

  • Kui Xu and Xiaojun Wan. Towards a Universal Sentiment Classifier in Multiple Languages. In EMNLP 2017. (Full Paper)

  • Junjie Cao, Sheng Huang, Weiwei Sun and Xiaojun Wan. Quasi-Second-Order Parsing for 1-Endpoint-Crossing, Pagenumber-2 Graphs. In EMNLP 2017. (Full Paper)

  • Jianmin Zhang and Xiaojun Wan. Towards Automatic Construction of News Overview Articles by News Synthesis. In EMNLP 2017. (Short Paper)

  • Liunian Li, Xiaojun Wan, Jin-ge Yao and Siming Yan. Leveraging Diverse Lexical Chains to Construct Essays for Chinese College Entrance Examination. In IJCNLP 2017. (Short Paper)

  • Shikang Du, Xiaojun Wan and Yajie Ye. Towards Automatic Generation of Entertaining Dialogues in Chinese Crosstalks. arXiv:1711.00294. (PDF)

2016

  • Xinjie Zhou, Xiaojun Wan, Jianguo Xiao. CMiner: Opinion Extraction and Summarization for Chinese Microblogs. IEEE Transactions on Knowledge and Data Engineering (TKDE).

  • Weiwei Sun, Xiaojun Wan. Towards Accurate and Efficient Chinese Part-of-Speech Tagging. Computational Linguistics.

  • Xun Zhang, Yantao Du, Weiwei Sun, Xiaojun Wan. Transition-based Parsing for Deep Dependency Structures. Computational Linguistics.

  • Xiaojun Wan and Tianming Wang. Automatic Labeling of Topic Models Using Text Summaries. In ACL 2016. (Full Paper)

  • Jianmin Zhang, Jin-ge Yao and Xiaojun Wan. Toward Constructing Sports News from Live Text Commentary. In ACL 2016. (Full Paper, PDF, dataset)

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning. In ACL 2016. (Full Paper)

  • Yang Yu, Xiaojun Wan and Xinjie Zhou. User Embedding for Scholarly Microblog Recommendation. In ACL 2016. (Short Paper)

  • Jin-ge Yao, Feifan Fan, Wayne Xin Zhao, Xiaojun Wan, Edward Chang, Jianguo Xiao. Tweet Timeline Generation with Determinantal Point Processes. In AAAI 2016. (Full Oral Paper)

  • Yang Yu and Xiaojun Wan. MicroScholar: Mining Scholarly Information from Chinese Microblogs. In AAAI 2016. (Student Poster Paper)

  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. A Neural Network Approach to Quote Recommendation in Writings. In CIKM 2016. (Full Paper)

  • Ziwei Zheng and Xiaojun Wan. Graph-Based Multi-Modality Learning for Clinical Decision Support. In CIKM 2016. (Short Paper)

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. Attention-based LSTM Network for Cross-Lingual Sentiment Classification. In EMNLP 2016. (Full Paper)

  • Jianmin Zhang, Tianming Wang and Xiaojun Wan. PKUSUMSUM: A Java Platform for Multilingual Document Summarization. In COLING 2016. (Demo Paper, project)

2015

  • Su Yan, Xiaojun Wan. Deep Dependency Sub-Structure Based Learning for Multi-Document Summarization. ACM Transactions on Information Systems (TOIS).

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. CLOpinionMiner: Opinion Target Extraction in a Cross-Language Scenario. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP).

  • Yue Hu and Xiaojun Wan. PPSGen: Learning-Based Presentation Slides Generation for Academic Papers. IEEE Transactions on Knowledge and Data Engineering (TKDE).

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. Representation Learning for Aspect Category Detection in Online Reviews. In AAAI 2015. (Full Oral Paper)

  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. Learning to Recommend Quotes for Writing. In AAAI 2015. (Full Oral Paper, Errata, Corrected PDF)

  • Jin-ge Yao, Xiaojun Wan and Jianguo Xiao. Compressive Document Summarization via Sparse Optimization. In IJCAI 2015. (Full Oral Paper)

  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. Joint Matrix Factorization and Manifold-Ranking for Topic-Focused Multi-Document Summarization. In SIGIR 2015. (Short Paper)

  • Yantao Du, Weiwei Sun and Xiaojun Wan. A Data-Driven, Factorization Parser for CCG Dependency Structures. In ACL 2015. (Full Oral Paper)

  • Xiaojun Wan and Yue Hu. BrailleSUM: A News Summarization System for the Blind and Visually Impaired People. In ACL 2015. (Short Paper)

  • Jin-ge Yao, Xiaojun Wan and Jianguo Xiao. Phrase-based Compressive Cross-Language Summarization. In EMNLP 2015. (Long Paper)

  • Xiaojun Wan, Ziqiang Cao, Furu Wei, Sujian Li, Ming Zhou. Multi-Document Summarization via Discriminative Summary Reranking. arXiv:1507.02062. (PDF)

  • Yue Hu, Xiaojun Wan. Mining and Analyzing the Future Works in Scientific Articles. arXiv:1507.02140. (PDF)

  • Xiaojun Wan, Yansong Feng, Weiwei Sun. Automatic Text Generation: Research Progress and Future Trends. Book Chapter in CCF 2014-2015 Annual Report on Computer Science and Technology in China (In Chinese), China Machine Press, 2015. PDF

2014

  • Su Yan and Xiaojun Wan. SRRank: Leveraging Semantic Roles for Extractive Multi-Document Summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP).

  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. Comparative News Summarization Using Concept-based Optimization. Knowledge and Information Systems (KAIS).

  • Xiaojun Wan and Fang Liu. WL-Index: Leveraging Citation Mention Number to Quantify an Individual’s Scientific Impact. Journal of the American Society for Information Science and Technology (JASIST).

  • Xiaojun Wan and Fang Liu. Are Literature Citations Equally Important? Automatic Citation Strength Estimation and Its Applications. Journal of the American Society for Information Science and Technology (JASIST).

  • Xiaojun Wan and Jianmin Zhang. CTSUM: Extracting More Certain Summaries for News Articles. In SIGIR 2014. (Full Oral paper)

  • Xuewei Tang, Xiaojun Wan, Xun Zhang. Cross-language Context-Aware Citation Recommendation in Scientific Articles. In SIGIR 2014. (Full Oral paper)

  • Shiyang Wen and Xiaojun Wan. Emotion Classification in Microblog Texts Using Class Sequential Rules. In AAAI 2014. (Full Oral paper)

  • Weiwei Sun, Yantao Du, Xin Kou, Shuoyang Ding and Xiaojun Wan. Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing. In ACL 2014. (Full Oral paper)

  • Yue Hu and Xiaojun Wan. Automatic Generation of Related Work Sections in Scientific Papers: An Optimization Approach. In EMNLP 2014. (Full Oral Paper)

  • Jinge Yao, Xiaojun Wan and Jianguo Xiao. Joint Decoding for Tree-Transductive Sentence Compression. In EMNLP 2014. (Short Oral Paper)

  • Xiaojun Wan. x-index: a fantastic new indicator for quantifying a scientist's scientific impact. arXiv:1405.0641. (PDF)

2013

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. Collective Opinion Target Extraction in Chinese Microblogs. In EMNLP 2013. (Full Oral paper)

  • Weiwei Sun and Xiaojun Wan. Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing. Transactions of the Association for Computational Linguistics(TACL). (Oral Presentation in ACL2013)

  • Xiaojun Wan. Subtopic-Based Multi-Modality Ranking for Topic-Focused Multi-Document Summarization. Computational Intelligence.

  • Yue Hu and Xiaojun Wan. PPSGen: Learning to Generate Presentation Slides for Academic Papers. In IJCAI 2013.

  • Shanshan Huang, Xiaojun Wan, Xuewei Tang. AMRec: An Intelligent System for Academic Method Recommendation. In AAAI 2013. (Late-breaking short paper)

  • Jiwei Tan, Xiaojun Wan, Jianguo Xiao. Learning to Order Natural Language Texts. In ACL 2013. (short oral paper)

  • Xiaojun Wan. Co-Regression for Cross-Language Review Rating Prediction. In ACL 2013. (short paper)

  • Shanshan Huang, Xiaojun Wan. AKMiner: Domain-Specific Knowledge Graph Mining from Academic Literatures. In WISE 2013. (Full paper)

  • Weiwei Sun, Xiaochang Peng and Xiaojun Wan. Capturing Long-distance Dependencies in Sequence Models: A Case Study of Chinese Part-of-speech Tagging. In IJCNLP 2013.

2012

  • Liqiang Guo, Xiaojun Wan. Exploiting Syntactic and Semantic Relationships between Terms for Opinion Retrieval. Journal of the American Society for Information Science and Technology (JASIST), 63(11):2269-2282.

  • Liqiang Guo, Xiaojun Wan. S2ORM: Exploiting Syntactic and Semantic Information for Opinion Retrieval. In WWW 2012, pages 517-518. (Poster Paper)

  • Weiwei Sun, Xiaojun Wan. Reducing approximation and estimation errors for Chinese lexical processing with heterogeneous annotations. In ACL 2012, pages 232-241. (Long Paper)

  • Rui Yan, Xiaojun Wan, Mirella Lapata, Pu-Jen Cheng, Xiaoming Li. Visualizing Timelines: Evolutionary Summarization via Iterative Reinforcement between Text and Image Streams. In CIKM 2012, pages 275-284. (Full Paper)

  • Xinjie Zhou, Xiaojun Wan, Jianguo Xiao. Cross-Language Opinion Target Extraction in Review Texts. In ICDM 2012, pages 1200-1205. (Short Oral Paper)

  • Xiaojun Wan. Update Summarization Based on Co-Ranking with Constraints. In COLING 2012, pages 1291-1300. (Poster Paper)

2011

  • Xiaojun Wan. Bilingual Co-training for Sentiment Classification of Chinese Product Reviews. Computational Linguistics, 37(3): 587-616. (dataset)

  • Xiaojun Wan. Using Bilingual Information for Cross-Language Document Summarization. In ACL 2011, pages 1546-1555. (Long Paper)

  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. Comparative News Summarization Using Linear Programming. In ACL 2011, pages 648-653. (Short Paper)

  • Xiaojun Wan, Houping Jia, Shanshan Huang, Jianguo Xiao. Summarizing the Differences in Multilingual News. In SIGIR 2011, pages 735-744. (Full Paper)

  • Rui Yan, Xiaojun Wan, Jahna Otterbacher, Liang Kong, Xiaoming Li, Yan Zhang. Evolutionary Timeline Summarization: a Balanced Optimization Framework via Iterative Substitution. In SIGIR 2011, pages 745-754. (Full Paper)

  • Rui Yan, Liang Kong, Congrui Huang, Xiaojun Wan, Xiaoming Li, Yan Zhang. Timeline Generation through Evolutionary Trans-Temporal Summarization. In EMNLP 2011, pages 433-443. (Oral Paper)

  • Xiaojun Wan, Liang Zong, Xiaojiang Huang, Tengfei Ma, Houping Jia, Yuqian Wu, Jianguo Xiao. Named Entity Recognition in Chinese News Comments on the Web. In IJCNLP 2011, pages 856-864. (Full Paper, dataset)

  • Huiying Li, Yue Hu, Zeyuan Li, Xiaojun Wan, Jianguo Xiao. PKUTM participation at TAC 2011 Summarization Track. In TAC 2011. (System Report. We ranked 1st and 2nd over the pyramid and overall responsiveness metrics for the initial summaries on the Guided Summarization task, respectively, and ranked 2nd and 3rd over the overall responsiveness and pyramid metrics for the update summaries on the AESOP task, respectively. )

2010

  • Xiaojun Wan, Jianguo Xiao. Exploiting Neighborhood Knowledge for Single Document Summarization and Keyphrase Extraction. ACM Transactions on Information Systems(TOIS), Volume 28, Issue 2, Article 8, 34 pages.

  • Xiaojun Wan, Huiying Li, Jianguo Xiao. Cross-Language Document Summarization Based on Machine Translation Quality Prediction. In ACL 2010, pages 917-926. (Full Paper)

  • Xiaojun Wan, Huiying Li, Jianguo Xiao. EUSUM: Extracting Easy-to-Understand English Summaries for Non-Native Readers. In SIGIR 2010, pages 491-498. (Full Paper)

  • Xiaojun Wan, Jianwu Yang. A practical system for harvesting and monitoring hot topics on the web. In WWW 2010, pages 1197-1198. (Poster Paper)

  • Xiaojun Wan. Towards a Unified Approach to Simultaneous Single-Document and Multi-Document Summarizations. In COLING 2010, pages 1137-1145. (Oral Paper)

  • Tengfei Ma, Xiaojun Wan. Opinion Target Extraction in Chinese News Comments. In COLING 2010, pages 782-790. (Poster Paper, dataset)

  • Tengfei Ma, Xiaojun Wan. Multi-Document Summarization Using Minimum Distortion. In ICDM 2010, pages 354-363. (Regular Paper)

  • Chenfeng Wang, Tengfei Ma, Liqiang Guo, Xiaojun Wan, Jianwu Yang. PKUTM Experiments in NTCIR-8 MOAT Task. In Proceedings of the 8th NTCIR Workshop Meeting (NTCIR-8), pages 228-233. (System Report. We ranked 1st in both the opinionated and holder subtasks for Simplified Chinese.)

  • Houping Jia, Xiaojiang Huang, Tengfei Ma, Xiaojun Wan, Jianguo Xiao. PKUTM Participation at TAC 2010 RTE and Summarization Tracks. In Proceedings of the 2010 Text Analysis Conference (TAC 2010). (System Report. We ranked 1st in both Main and Novelty Detection Tasks at RTE-6)

2009

  • Xiaojun Wan. Co-Training for Cross-Lingual Sentiment Classification. In ACL-IJCNLP 2009, pages 235-243. (Full Paper, dataset)

  • Xiaojun Wan, Jianguo Xiao. Graph-Based Multi-Modality Learning for Topic-Focused Multi-Document Summarization. In IJCAI 2009, pages 1586-1591. (Oral Paper)

  • Xiaojun Wan. Topic Analysis for Topic-Focused Multi-Document Summarization. In CIKM 2009, pages 1609-1612. (Short Paper)

2008

  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Towards a Unified Approach to Document Similarity Search Using Manifold-Ranking of Blocks. Information Processing & Management, 44(3): 1032-1048.

  • Xiaojun Wan. Using Only Cross-Document Relationships for Both Generic and Topic-Focused Multi-Document Summarizations. Information Retrieval, 11(1): 25-49.

  • Xiaojun Wan. CM-PMI: Improved Web-based Association Measure with Contextual Label Matching. In WWW 2008, pages 1079-1080. (Poster Paper)

  • Xiaojun Wan, Jianguo Xiao. Single Document Keyphrase Extraction Using Neighborhood Knowledge. In AAAI 2008, pages 855-860. (Oral Paper, dataset)

  • Xiaojun Wan, Jianwu Yang. Multi-Document Summarization Using Cluster-based Link Analysis. In SIGIR 2008, pages 299-306. (Regular Paper)

  • Xiaojun Wan, Jianguo Xiao. CollabRank: Towards a Collaborative Approach to Single-Document Keyphrase Extraction. In COLING 2008, pages 969-976. (Oral Paper)

  • Xiaojun Wan. An Exploration of Document Impact on Graph-Based Multi-Document Summarization. In EMNLP 2008, pages 755-762. (Full Oral Paper)

  • Xiaojun Wan. Using Bilingual Knowledge and Ensemble Techniques for Unsupervised Chinese Sentiment Analysis. In EMNLP 2008, pages 553-561. (Full Poster Paper, dataset)

2007 and Prior

  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Manifold-ranking based topic-focused multi-document summarization. In IJCAI 2007, pages 2903-2908. (Oral Paper)

  • Xiaojun Wan, Jianwu Yang. Learning Information Diffusion Process on the Web. In WWW 2007, pages 1173-1174. (Poster Paper)

  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Towards an Iterative Reinforcement Approach for Simultaneous Document Summarization and Keyword Extraction. In ACL 2007, pages 552-559. (Full Paper, Errata, Corrected PDF)

  • Xiaojun Wan, Jianwu Yang. Single Document Summarization with Document Expansion. In AAAI 2007, pages 931-936. (Oral Paper)

  • Xiaojun Wan, Jianwu Yang. CollabSum: Exploiting Multiple Document Clustering for Collaborative Single Document Summarizations. In SIGIR 2007, pages 143-150. (Regular Paper)

  • Xiaojun Wan. OMES: a new evaluation strategy using optimal matching for document clustering. In SIGIR 2007, pages 693-694. (Poster Paper)

  • Xiaojun Wan. TimedTextRank: adding the temporal dimension to multi-document summarization. In SIGIR 2007, pages 867-868. (Poster Paper)

  • Xiaojun Wan. A novel document similarity measure based on earth mover's distance. Information Sciences, 177(18): 3718-3730.

  • Xiaojun Wan, Jianwu Yang. Using Proportional Transportation Distances for measuring document similarity. In ECIR 2006, pages 25-36. (Oral Paper)

  • Xiaojun Wan, Jianwu Yang. Using Proportional Transportation Similarity with learned element semantics for XML document clustering. In WWW 2006, pages 961-962. (Poster Paper)

  • Xiaojun Wan, Jianwu Yang. Improved affinity graph based multi-document summarization. In HLT-NAACL 2006, pages 181-184. (Short Paper)

  • Xiaojun Wan, Jianfeng Gao, Mu Li, Binggong Ding. Person resolution in person search results: WebHawk. In CIKM 2005, pages 163-170. (Oral Paper)

  • Xiaojun Wan, Yuxin Peng. The Earth Mover’s Distance as a Semantic Measure for Document Similarity. In CIKM 2005, pages 301-302. (Poster Paper)

Return