Fangzheng (Frank) Xu

Master's Student

Advisor: Kenny Q. Zhu
SEIEE #3-341
Dept. of Computer Science & Engineering
Shanghai Jiao Tong University

Email: frankxu[at]sjtu.edu.cn
frankxu2004[at]gmail.com
Frank Xu Bio

Publications (Google Scholar)

CV/Resume

Links

My Twitter

Github


Bio

I am currently a research assistant at Carnegie Mellon University, working with Prof. Jeffrey Bigham. I recieved my Master's degree in Computer Science from ADAPT Lab, Shanghai Jiao Tong University in 2019, under the supervision of Prof. Kenny Q. Zhu. I have worked with Prof. Jiawei Han at UIUC, Prof. Xiang Ren at USC and Zhiting Hu at CMU on various NLP topics including text generation, commonsense knowledge, information extraction and text mining. Prior to that, I obtained B.Eng of Computer Science from IEEE Honored Class, Shanghai Jiao Tong University, and earned Best Thesis Award in SJTU Bachelor's Thesis Defense (Top 1%).

News


Research

I work in natural language processing, deep learning, knowledge acquisition/reasoning and AI for social good. I like to make NLP tasks feasible with less human effort by indirect or weak supervision and by building a two-way bridge between natural language text and structured knowledge, logic, relational data.

Some topics I am interested include text and code generation, contextualized and goal-oriented conversation, low-resource languages, reading comprehension, knowledge acquisition, reasoning and inference, grounded language learning, interpretable and structured models as well as NLP for social good.

My past research spans across natural language processing, deep learning, data mining and computational social science. More specifically: (a) cross-cultural, cross-lingual problems, (b) commonsense knowledge, (c) sequence labeling, (d) information extraction with weak or indirect supervision, (e) subword embedding, (f) controllable text generation, (g) social and urban computing.

I was a member of the Advanced Data And Programming Technology Lab (ADAPT-Lab) .

Research Directions

Good Research Advices


Publications (* indicates equal contribution)

Preprints

Toward Unsupervised Text Content Manipulation
Under anonymous submission

Parsimonious Morpheme Segmentation with an Application to Word Embeddings
Under anonymous submission

Incorporating Diversity into Influential Node Mining
Yu Zhang, Frank F. Xu, Tianshu Lyu, Xiang Ren, Jiawei Han.
[arXiv]

Conference Papers

Mining Cross-Cultural Differences and Similarities in Social Media.
Frank F. Xu*, Bill Y. Lin*, Kenny Q. Zhu, Seung-won Hwang.
In Proceedings of 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018

Automatic Extraction of Commonsense LocatedNear Knowledge.
Frank F. Xu*, Bill Y. Lin*, Kenny Q. Zhu.
In Proceedings of 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018

ExtRA: Extracting Prominent Review Aspects from Customer Feedback.
Zhiyi Luo, Shanshan Huang, Frank F. Xu, Bill Yuchen Lin, Hanyuan Shi, Kenny Zhu.
In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018

Empower Sequence Labeling with Task-Aware Neural Language Model.
Liyuan Liu, Jingbo Shang, Frank F. Xu, Xiang Ren, Huan Gui, Jian Peng, Jiawei Han.
In Proceedings of Thirty-second AAAI Conference on Artificial Intelligence (AAAI), 2018. [arXiv]

ReQuest: Indirect Supervision for Relation Extraction using Question-Answer Pairs.
Zeqiu Wu, Xiang Ren, Frank F. Xu, Ji Li, Jiawei Han.
In Proceedings of The 11th ACM International Conference on Web Search and Data Mining (WSDM), 2018. [arXiv]

Open Information Extraction with Global Structure Constraints.
Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Frank F. Xu, Jiawei Han.
In Proceedings of The Web Conference (WWW Poster), 2018. (Best Poster Award Honorable Mention)

Entropy-Based Subword Mining with an Application to Word Embeddings.
Ahmed El-Kishky, Frank F. Xu, Aston Zhang, Stephen Macke, Jiawei Han.
In Proceedings of the Second Workshop on Subword/Character LEvel Models (SCLeM) at NAACL, 2018.

Mining Cross-Cultural Differences of Named Entities: A Preliminary Study.
Frank F. Xu*, Bill Y. Lin*, Kenny Q. Zhu.
Appeared on First Workshop on Knowledge Base Construction, Reasoning and Mining (KBCOM) at WSDM, 2018.

Commonsense LocatedNear Relation Extraction.
Frank F. Xu*, Bill Y. Lin*, Kenny Q. Zhu.
Appeared on 6th Workshop on Automated Knowledge Base Construction (AKBC) at NIPS, 2017. [arXiv]

Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media.
Frank F. Xu*, Bill Y. Lin*, Zhiyi Luo, Kenny Q. Zhu.
In Proceedings of the 3rd Workshop on Noisy User-generated Text (W-NUT) at EMNLP, 2017. [PDF] (2nd place in the shared task)

Transfer Learning for Traffic Speed Prediction: A Preliminary Study.
Frank F. Xu*, Bill Y. Lin*, Eve Q. Liao, Kenny Q. Zhu
In Proceedings of SmartIoT 2018 Workshop: AI enhanced IoT data processing for Intelligent Applications, at AAAI, 2018

Cross-region Traffic Prediction for China on OpenStreetMap.
Frank F. Xu, Bill Y. Lin, Qi Lu, Yifei Huang and Kenny Q. Zhu.
In Proceedings of the 9th ACM SIGSPATIAL International Workshop on Computational Transportation Science, 2016. [PDF]

Thesis

Indirect Supervision for Information Extraction
Frank F. Xu
Master's Thesis, 2019. [PDF]

Traffic Prediction for Urban Planning
Frank F. Xu
Bachelor's Thesis (Best Thesis Award, Top 1% in SJTU, Top 1 in CSE department), 2016. [PDF][Slides][Poster][Video]


Useful Links

Gmail
SJTU CS
SJTU Webmail
My GitHub
My Twitter
My LinkedIn
My ResearchGate
NLP Calendar
Google Calendar
ADAPT Lab
DBLP
Google Scholar

This page was last updated on Jan. 22, 2019

This page was initially created on May 1, 2016