已发表论文

出自北京大学计算机科学技术研究所语言计算与互联网挖掘研究室

跳转到: 导航, 搜索

目录

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)

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, Acceptance rate for full oral paper is 12%)
  • Jiwei Tan, Xiaojun Wan and Jianguo Xiao. Learning to Recommend Quotes for Writing. In AAAI 2015. (Full Oral Paper, Acceptance rate for full oral paper is 12%)
  • 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)
  • Yantao Du, Fan Zhang, Xun Zhang, Weiwei Sun and Xiaojun Wan. Peking: Building Semantic Dependency Graphs with a Hybrid Parser. In SemEval 2015. (Oral Talk)
  • Xiaojun Wan, Jianmin Zhang, Shiyang Wen and Jiwei Tan. Overview of the NLPCC 2015 Shared Task: Weibo-Oriented Chinese News Summarization. In NLPCC 2015. (Invited Paper, PDF)
  • Xiaojun Wan, Ziqiang Cao, Furu Wei, Sujian Li, Ming Zhou. Multi-Document Summarization via Discriminative Summary Reranking. arxiv. (Technical Report)
  • Yue Hu, Xiaojun Wan. Mining and Analyzing the Future Works in Scientific Articles. arxiv. (Technical Report)
  • 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

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)
  • Xuewei Tang and Xiaojun Wan. Learning Bilingual Embedding Model for Cross-Language Sentiment Classification. In WI 2014. (Regular 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. (Technical Report)


2013

  • Xinjie Zhou, Xiaojun Wan and Jianguo Xiao. Collective Opinion Target Extraction in Chinese Microblogs. In EMNLP2013, pages XXX-XXX. (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).
  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. Comparative News Summarization Using Concept-based Optimization. Knowledge and Information Systems (KAIS), In Press.
  • Xiaojun Wan. Subtopic-Based Multi-Modality Ranking for Topic-Focused Multi-Document Summarization. Computational Intelligence, In Press.
  • Yue Hu and Xiaojun Wan. PPSGen: Learning to Generate Presentation Slides for Academic Papers. In IJCAI2013, pages XXX-XXX.
  • Shanshan Huang, Xiaojun Wan, Xuewei Tang. AMRec: An Intelligent System for Academic Method Recommendation. In AAAI2013, pages XXX-XXX. (short paper)
  • Jiwei Tan, Xiaojun Wan, Jianguo Xiao. Learning to Order Natural Language Texts. In ACL2013, pages XXX-XXX. (short oral paper)
  • Xiaojun Wan. Co-Regression for Cross-Language Review Rating Prediction. In ACL2013, pages XXX-XXX. (short paper)
  • Shanshan Huang, Xiaojun Wan. AKMiner: Domain-Specific Knowledge Graph Mining from Academic Literatures. In WISE2013, pages XXX-XXX. (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 IJCNLP2013.

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), pages XXX-XXX, In Press.
  • Liqiang Guo, Xiaojun Wan. S2ORM: Exploiting Syntactic and Semantic Information for Opinion Retrieval. In WWW2012, pages XXX-XXX. (Poster Paper)
  • Weiwei Sun, Xiaojun Wan. Reducing approximation and estimation errors for Chinese lexical processing with heterogeneous annotations. In ACL2012, pages XXX-XXX. (Long Paper)
  • Weiwei Sun and Hans Uszkoreit. Capturing paradigmatic and syntagmatic lexical relations: Towards accurate Chinese part-of-speech tagging. In ACL2012, pages XXX-XXX. (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 CIKM2012, pages XXX-XXX. (Full Paper)
  • Rui Yan, Zi Yuan, Xiaojun Wan, Yan Zhang, Xiaoming Li. Hierarchical Graph Summarization: Leveraging Hybrid Information through Visible and Invisible Linkage. In PAKDD2012, pages XXX-XXX. (Full Paper)
  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. BiCWS: Mining Cognition Differences from Bilingual Web Search Results. In WISE2012, pages 58-71. (Regular Paper)
  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. Learning to Find Comparable Entities on the Web. In WISE2012, pages 16-29. (Regular Paper)
  • Xiaojun Wan. A Comparative Study of Cross-Lingual Sentiment Classification. In WI2012, pages XXX-XXX. (Regular Paper)
  • Xiaojun Wan. Update Summarization Based on Co-Ranking with Constraints. In COLING2012, pages XXX-XXX.
  • Minwei Feng, Weiwei Sun and Hermann Ney. Semantic Cohesion Model for Phrase-based SMT. In COLING2012, pages XXX-XXX.
  • Xinjie Zhou, Xiaojun Wan, Jianguo Xiao. Cross-Language Opinion Target Extraction in Review Texts. In ICDM2012.

2011

  • Xiaojun Wan. Bilingual Co-training for Sentiment Classification of Chinese Product Reviews. Computational Linguistics, 37(3): 587-616.
  • Xiaojun Wan. Using Bilingual Information for Cross-Language Document Summarization. In ACL2011, pages 1546-1555. (Long Paper)
  • Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao. Comparative News Summarization Using Linear Programming. In ACL2011, pages 648-653. (Short Paper)
  • Xiaojun Wan, Houping Jia, Shanshan Huang, Jianguo Xiao. Summarizing the Differences in Multilingual News. In SIGIR2011, pages 735-744. (Full Paper, Acceptance Rate =19.8%)
  • Rui Yan, Xiaojun Wan, Jahna Otterbacher, Liang Kong, Xiaoming Li, Yan Zhang. Evolutionary Timeline Summarization: a Balanced Optimization Framework via Iterative Substitution. In SIGIR2011, pages 745-754. (Full Paper, Acceptance Rate =19.8%)
  • Rui Yan, Liang Kong, Congrui Huang, Xiaojun Wan, Xiaoming Li, Yan Zhang. Timeline Generation through Evolutionary Trans-Temporal Summarization. In EMNLP2011, pages 433-443. (Oral Paper, Acceptance Rate =15%)
  • Xiaojun Wan. Collaborative Data Cleaning for Sentiment Classification with Noisy Training Corpus. In PAKDD2011, pages 326-337. (Short Oral Presentation)
  • 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 IJCNLP2011, pages 856-864. (Full Oral Paper)
  • Huiying Li, Yue Hu, Zeyuan Li, Xiaojun Wan, Jianguo Xiao. PKUTM participation at TAC 2011 Summarization Track. In TAC2011.

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 ACL2010, pages 917-926. (Full Paper, Acceptance Rate = 25%)
  • Xiaojun Wan, Huiying Li, Jianguo Xiao. EUSUM: Extracting Easy-to-Understand English Summaries for Non-Native Readers. In SIGIR2010, pages 491-498. (Full Paper, Acceptance Rate = 16.7%)
  • Xiaojun Wan, Jianwu Yang. A practical system for harvesting and monitoring hot topics on the web. In WWW2010, pages 1197-1198. (Poster Paper)
  • Xiaojun Wan. Towards a Unified Approach to Simultaneous Single-Document and Multi-Document Summarizations. In COLING2010, pages 1137-1145. (Oral Paper, Acceptance Rate = 19%)
  • Tengfei Ma, Xiaojun Wan. Opinion Target Extraction in Chinese News Comments. In COLING2010, pages 782-790. (Poster Paper)
  • Tengfei Ma, Xiaojun Wan. Multi-Document Summarization Using Minimum Distortion. In ICDM2010, pages 354-363. (Regular Paper, Acceptance Rate=9%)
  • Liang Zong, Xiaojun Wan, Lihong Zhao, Jianwu Yang, Yuqian Wu. Named Entity Resolution in Chinese News Comments on the Web. In APWeb2010, pages 307-313. (Full 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.
  • 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 (TAC2010).

2009

  • Xiaojun Wan. Co-Training for Cross-Lingual Sentiment Classification. In ACL-IJCNLP2009, pages 235-243. (Full Paper, Acceptance Rate = 21%)
  • Xiaojun Wan, Jianguo Xiao. Graph-Based Multi-Modality Learning for Topic-Focused Multi-Document Summarization. In IJCAI2009, pages 1586-1591. (Oral Paper, Acceptance Rate = 25.7%)
  • Xiaojun Wan. Topic Analysis for Topic-Focused Multi-Document Summarization. In CIKM2009, pages 1609-1612. (Short Paper)
  • Xiaojun Wan, Jianguo Xiao. Towards a Novel Association Measure via Web Search Results Mining. In PAKDD2009, pages 804-812. (Short Oral Paper)
  • Xiaojun Wan. Combining Content and Context Similarities for Image Retrieval. In ECIR2009, pages 749-754. (Poster 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. Beyond topical similarity: a structural similarity measure for retrieving highly similar documents. Knowledge and Information Systems, 15(1): 55-73.
  • Xiaojun Wan. CM-PMI: Improved Web-based Association Measure with Contextual Label Matching. In WWW2008, pages 1079-1080. (Poster Paper)
  • Xiaojun Wan, Jianguo Xiao. Single Document Keyphrase Extraction Using Neighborhood Knowledge. In AAAI2008, pages 855-860. (Oral Paper, Acceptance Rate = 24%)
  • Xiaojun Wan, Jianwu Yang. Multi-Document Summarization Using Cluster-based Link Analysis. In SIGIR2008, pages 299-306. (Regular Paper, Acceptance Rate = 17%)
  • Xiaojun Wan, Jianguo Xiao. CollabRank: Towards a Collaborative Approach to Single-Document Keyphrase Extraction. In COLING2008, pages 969-976. (Oral Paper, Acceptance Rate = 26.8%)
  • Xiaojun Wan. An Exploration of Document Impact on Graph-Based Multi-Document Summarization. In EMNLP2008, pages 755-762. (Full Oral Paper, Acceptance Rate = 21%)
  • Xiaojun Wan. Using Bilingual Knowledge and Ensemble Techniques for Unsupervised Chinese Sentiment Analysis. In EMNLP2008, pages 553-561. (Full Poster Paper, Acceptance Rate [Oral+Poster] = 30%)
  • Xiaojiang Huang, Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Learning to Identify Comparative Sentences in Chinese Text. In PRICAI2008, pages 187-198. (Oral Long Paper)

2007 and before

  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Manifold-ranking based topic-focused multi-document summarization. In IJCAI2007, pages 2903-2908. (Oral Paper, Acceptance Rate = 15.7%)
  • Xiaojun Wan, Jianwu Yang. Learning Information Diffusion Process on the Web. In WWW2007, pages 1173-1174. (Poster Paper)
  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Towards an Iterative Reinforcement Approach for Simultaneous Document Summarization and Keyword Extraction. In ACL2007, pages 552-559. (Full Paper, Acceptance Rate = 22.3%)
  • Xiaojun Wan, Jianwu Yang. Single Document Summarization with Document Expansion. In AAAI2007, pages 931-936. (Oral Paper, Acceptance Rate = 27%)
  • Xiaojun Wan, Jianwu Yang. CollabSum: Exploiting Multiple Document Clustering for Collaborative Single Document Summarizations. In SIGIR2007, pages 143-150. (Regular Paper, Acceptance Rate = 18.5%)
  • Xiaojun Wan. OMES: a new evaluation strategy using optimal matching for document clustering. In SIGIR2007, pages 693-694. (Poster Paper)
  • Xiaojun Wan. TimedTextRank: adding the temporal dimension to multi-document summarization. In SIGIR2007, pages 867-868. (Poster Paper)
  • Xiaojun Wan, Jianguo Xiao. Towards a Unified Approach Based on Affinity Graph to Various Multi-document Summarizations. In ECDL2007, pages 297-308. (Oral 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 ECIR2006, pages 25-36. (Oral Paper)
  • Xiaojun Wan, Jianwu Yang. Using Proportional Transportation Similarity with learned element semantics for XML document clustering. In WWW2006, pages 961-962. (Poster Paper)
  • Xiaojun Wan, Jianwu Yang. Improved affinity graph based multi-document summarization. In HLT-NAACL2006, pages 181-184. (Short Paper)
  • Xiaojun Wan, Jianwu Yang, Jianguo Xiao. Using cross-document random walks for topic-focused multi-document summarization. In WI2006, pages 1012-1018. (Regular Paper)
  • Xiaojun Wan, Jianfeng Gao, Mu Li, Binggong Ding. Person resolution in person search results: WebHawk. In CIKM2005, pages 163-170. (Oral Paper, Acceptance Rate = 18%)
  • Xiaojun Wan, Yuxin Peng. The Earth Mover’s Distance as a Semantic Measure for Document Similarity. In CIKM2005, pages 301-302. (Poster Paper)
个人工具