Lu Wang 王璐
Lu Wang is an Assistant Professor of College of Computer and Information Science at Northeastern University since 2015. She is also affiliated with Northeastern NLP group and NULab for Texts, Maps, and Networks. She completed her Ph.D. in the Department of Computer Science at Cornell University, under supervision of Professor Claire Cardie in 2015.
Lu's research is focused on natural language processing, computational social science, and machine learning. More specifically, Lu works on algorithms for abstractive text summarization, language generation, argument mining, information extraction, and discourse analysis, as well as novel applications that apply such techniques to computational social science and other interdisciplinary subjects. Her work won outstanding short paper award at ACL 2017, and best paper nomination award at SIGDIAL 2012.
Lu's work has been mainly funded by National Science Foundation (NSF), Intelligence Advanced Research Projects Activity (IARPA), and several industry gifts (Tencent AI Lab, Toutiao AI Lab, NVIDIA GPU program, and Amazon Web Service credits).
Announcements
-
Spring 2018
-
Fall 2017
Interviewed and quoted in CNN article Offensive chat app responses highlight AI fails.
-
Current
For prospective Ph.D. students, post-docs, visitors, and undergrads who are interested in doing research with me, please read related notes on the Contact page first, and then fill in this external contact form.
Academic Position
-
Present 2015
Assistant Professor
Northeastern University, College of Computer and Information Science
Education
-
Ph.D. 2015
Ph.D., Computer Science
Cornell University
-
B.Sc.2009
Intelligence Science and Technology
Peking University
-
B.Econ.2009
Economics
Peking University
Grants
-
2017–2021Intelligence Advanced Research Projects Activity"Machine Translation for English Retrieval of Information in Any Language (MATERIAL)", subcontract to USC ISI.
-
2016–2018National Science Foundation CRII"Towards Abstractive Summarization of Meetings", PI.
-
2017–2018Northeastern University Tier 1"Inferring Argument Structure from Online and Live Conversations", PI with Nick Beauchamp and Michelle Borkin.
-
2017–2018Gift from Tencent AI Lab
-
2017–2018Gift from Toutiao AI Lab
-
2016–2017Northeastern University Tier 1"Dynamic Heterogeneous Information Networks for Intelligent Visual Forecasting", PI with Yun Raymond Fu.
-
2016, 2017NVIDIA GPU Grants
Research Summary
My research aims at designing robust Natural Language Processing (NLP) models that can automatically understand and learn from large-scale texts of various domains and genres, and produce summaries of high quality. More specically, I endeavor building NLP systems to automatically generate high quality text summaries from disparate sources such as meeting dialogues, newswire services, and social media data, as well as to create novel applications based on text generation techniques.
The second research direction of my group is understanding social interaction via the lens of argument mining. In this direction, we focus on conversation understanding via content and social interaction modeling. We also design linguistic analysis and representation learning-based algorithms for automatic detection of salient arguments and their relations.
Interests
- Text Summarization
- Language Generation
- Argument Mining
- Information Extraction
- Discourse Analysis
- Computational Social Science
- Machine Learning
Group Members
-
Xinyu Hua Site
Ph.D. student (2016–Present)
ACL outstanding short paper award, 2017
Argument mining (ACL'17)
Neural abstractive summarization (EMNLP NewSum'17)
-
Lisa Fan Site
Ph.D. student (2017–Present)
International Conference on Intelligent Virtual Agents (IVA) best paper nomination, 2017
Human robotics interaction (IVA'17)
Publications
Filter by type:
Sort by year:
Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems
Conference Paper
Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2014.
One of the Two Award Papers of Spoken
Language Processing Student Travel Award.
[link]
CornPittMich Sentiment Slot-Filling System at TAC 2014
Non-refereed Publication
Proceedings of the TAC-KBP 2014 Workshop, 2014.
Won Second Place in Sentiment Slot-Filling Track.
Data
Datasets for recent publications can be found at project pages (see corresponding publication entries) or Northeastern NLP group page.
Microblog Conversation Recommendation Corpus (First Release, 2018)
- Twitter conversations collected from TREC and from 2016 U.S. election.
-
DATA (.zip)
README (.txt) - This corpus is distributed together with:
Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse
Xingshan Zeng, Jing Li, Lu Wang, Nicholas Beauchamp, Sarah Shugars, and Kam-Fai Wong
Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018.
Movie Review and Online Argument Corpus (First Release, 2016)
-
Movie critics and their consensus from Rotten Tomatoes.
Online arguments from idebate.org. -
DATA (.zip)
README (.txt) - This corpus is distributed together with:
Neural Network-Based Abstract Generation for Opinions and Arguments
Lu Wang and Wang Ling
Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2016.
Socially-Informed Timeline Generation Corpus (First Release, 2015)
-
New York Times, CNN, and BBC news articles and user comments on four major events happened in 2014.
New York Times news articles and user comments in 2013. -
DATA (.zip)
README (.txt) - This corpus is distributed together with:
Socially-Informed Timeline Generation for Complex Events
Lu Wang, Claire Cardie, and Galen Marchetti
Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2015.
Wikipedia Disputed Discussion Corpus (First Release, 2016)
- Dispute and non-dispute discussions from Wikipedia talkpages.
-
DATA (.zip)
README (.txt) - This corpus is distributed together with:
A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection
Lu Wang and Claire Cardie
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), 2014.
Services
Selected Professional Services
- Area Co-chair: NAACL 2018 (Summarization), ACL 2016 (Summarization)
- Senior Program Committee: AAAI 2018
- Tutorial Co-chair: EMNLP 2018
- Workshop Co-organizer: Workshop on New Frontiers in Summarization at EMNLP 2017
- Member, Program Committee:
- ACL (2018, 2017, 2015, 2014, 2013)
- NAACL 2015
- EMNLP (2017, 2016, 2015, 2014)
- ICML 2018
- COLING 2016
- AISTATS 2017
- AAAI (2018, 2017, 2016)
- IJCAI 2016
- ICWSM (2018, 2017, 2014)
- WWW 2014
- Reviewer:
- Transactions of the Association for Computational Linguistics
- Journal of Artificial Intelligence Research
- Speech Communication
- IEEE Transactions on Knowledge and Data Engineering
- Transactions on Audio, Speech and Language Processing
- Funding Agency Panelist: National Science Foundation (2017 for CISE, 2016 for CISE and SBE)
Teaching
Current Course
-
Spring 2018
CS 6120/4120 - Natural Language Processing. Northeastern University.
Past Courses
-
Fall 2017
CS 6120/4120 - Natural Language Processing. Northeastern University.
-
Spring 2017
CS 6140 - Machine Learning. Northeastern University.
-
Sprint 2016
CS 6140 - Machine Learning. Northeastern University.
-
Fall 2015
CS 7180 - Special Topics in Artifical Intelligence. Northeastern University.
Contact
- luwang[at]ccs[dot]neu[dot]edu
- 258 West Village H, 440 Huntington Ave, Boston, MA 02115
To Prospective Ph.D. Students, Post-docs, and Vistors
I'm interested in doing research in natural language processing (NLP), where I design machine learning algorithms and computational models (e.g., neural networks, stochastic algorithms, probabilistic models, etc) for tasks on abstractive text summarization, language generation, argumentation mining, discourse analysis, and dialog analysis. I'm also interested in applying NLP and machine learning techniques for interdisciplinary subjects, e.g. computational social science. Specifically, there are four major ongoing research projects:
- Abstractive Text Summarization: We tackle the challenge of extracting key information from large amounts of textual data. We aim to generate concise and informative summaries for different types of texts, ranging from news articles in traditional media, to socially-generated content in popular social media (e.g. comments, tweets, or blogs), and to government meetings (e.g. Federal Reserve board meetings). Neural network-based methods are developed, with traditional training methods, multi-task learning, or reinforcement learning-based methods.
- Argumentation Mining: Arguments play an important role for decision-making processes and persuasion. We are interested in understanding how people argue with and influence others, as well as form their own opinions on topics of interest. Especially, we want to discover linguistic patterns that reflect these processes, and use them for social interaction analysis and prediction. NLP models for discourse and semantic analysis are investigated for this project.
- Argument Generation: In this project we aim to automate the process of generating persuasive arguments for different targeting audience or based on user's information request. This would need a better understanding of many aspects of high quality arguments, including discourse, semantic, and linguistic style. There is a wide range of applications, from improving essay writing and online argumentation skills, to enhancing public deliberation and political debate quality.
- Information Extraction: We work on semantic understanding of text from different domains, including both news articles and user comments. Concretely, our goal is to advance the state-of-the-art methods on mention detection, entity extraction, and entity linking tasks.
If any of these sounds interesting to you, please check out more about my research and papers at this website. My students and I are also part of Northeastern NLP group. If you find your research agenda might be aligned with mine and are interested in working with me, please fill in this external contact form and (for Ph.D. applicants) apply to College of Computer and Information Science (CCIS) at Northeastern University and mention my name in your application.
To Undergrad Students Interested in NLP Research
Please feel free to reach out using this external contact form . Prerequisites include being able to write code in some programming languages (e.g. Python, Java, C/C++) proficiently, and finishing courses in algorithms, multivariable calculus, probability, statistics, and linear algebra. It would be better that you have taken a course in natural language processing (CS4120/CS6120) or machine learning (CS4140/CS6140).