|
Lingjia Deng
PhD student
|
About
Hi! My name is Lingjia Deng. I am a fifth-year PhD student in Intelligent System Program at University of Pittsburgh since Fall 2011. Currently I'm working with Dr. Jan Wiebe. Welcome to check our groups's work of MPQA in sentiment analysis and opinion mining. Here is my CV.
ResearchMy research interests include Natural Language Processing and Machine Learning, focusing on opinion mining and sentiment analysis. Currently I am interested in opinion extraction and inference, especially opinions related to a common type of event. We name the event as "+/- Effect Event", which either benefit or harm the theme (object) of the event. Such event is quite common in online political editorials. People may not express their opinions directly, but rather present their stances toward one of the entities involed in such event. By inference, we can analyze people's opinions of the other entities in the event. For a detailed explaination, please refer to our coding manual. The corpus is also available online. PublicationsLingjia Deng and Janyce Wiebe (2016). Recognizing Opinion Sources Based on A New Categorization of Opinion Types. Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016. (IJCAI-2016) Lingjia Deng and Janyce Wiebe (2016). How can NLP Tasks Mutually Benefit Sentiment Analysis? A Holistic Approach to Sentiment Analysis. Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. (WASSA-2016) Lingjia Deng and Janyce Wiebe (2015). Joint Prediction for Entity/Event-Level Sentiment Analysis using Probabilistic Soft Logic Models. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015. (EMNLP-2015) Lingjia Deng and Janyce Wiebe (2015). MPQA 3.0: Entity/Event-Level Sentiment Corpus. Proceedings of NAACL-HLT, 2015. (NAACL-2015, short paper) Lingjia Deng (2015). Entity/Event-Level Sentiment Detection and Inference. Proceedings of NAACL-HLT Student Research Workshop, 2015. (Thesis Proposal) Lingjia Deng, Janyce Wiebe and Yoonjung Choi (2014). Joint Inference and Disambiguation of Implicit Sentiments via Implicature Constraints. Proceedings of COLING, 2014. (COLING-2014) Janyce Wiebe and Lingjia Deng (2014). An account of opinion implicatures. arXiv:1404.6491v1 [cs.CL] Lingjia Deng and Janyce Wiebe (2014). An Investigation for Implicatures in Chinese: Implicatures in Chinese and in English are similar! Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA-2014) Janyce Wiebe and Lingjia Deng (2014). A Conceptual Framework for Inferring Implicatures. Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA-2014) Yoonjung Choi, Janyce Wiebe and Lingjia Deng (2014). Lexical Acquisition for Opinion Inference: A Sense-Level Lexicon of Benefactive and Malefactive Events. Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA-2014) Lingjia Deng and Janyce Wiebe (2014). Sentiment Propagation via Implicature Constraints. Meeting of the European Chapter of the Association for Computational Linguistics (EACL-2014). Lingjia Deng, Janyce Wiebe, and Yoonjung Choi (2013). Benefactive/Malefactive Event and Writer Attitude Annotation. Annual Meeting of the Association for Computational Linguistics (ACL-2013, short paper). Banea, C., Choi, Yoonjung, Deng, L., Hassan, S., Mohler, M., Yang, B., Cardie, C., Mihalcea, R., and Wiebe, J. (2013). CPN-CORE: A Text Semantic Similarity System Infused with Opinion Knowledge. Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity. pp. 221-228. Association for Computational Linguistics. Courses Taken
MiscWelcome to join us at Natural Language Group at University of Pittsburgh.If you're Chinese and interested in Natural Language Processing, the 52nlp site is a good place to start. Strongly recommend two TV-series: Criminal Minds on CBS and Hustle from BBC. Thank Zhen Qin for the HTML template and the firefox browser is amazingly able to inspect element and provide the HTML code. Last Modified: 09/10/2015 15:11:16 EST |