Avatar

Li "Harry" Zhang  张力


About Me

I am a second-year PhD student focusing on Natural Language Processing, working with Prof. Chris Callison-Burch at the University of Pennsylvania. I graduated from the University of Michigan in 2018, previously mentored by Prof. Rada Mihalcea and Prof. Dragomir Radev. I'm also a competitive pool player and a passionate amateur multi-instrumental musician! I love playing metal, rock, funk and fusion.

CV   Publications        

University of Pennsylvania

Shenzhen, China

zharry@seas.upenn.edu


Music

I play, record and produce music. Sometimes I play multiple instruments myself; sometimes I play with my talented friends. More of my work can be found on Bilibili.


I'm an intermediate-to-advanced drummer. I play a Roland TD-30K electronic set with Tama Speed Cobra 910 pedals.

I'm also a beginner-to-intermediate guitarist and bassist. I play a Schecter C-7 FR-S Apocalypse electric guitar and an Ibanez GSRM20 Mikro electric bass.


Pool

I'm a decent pool player. I used to play competitively in the university team and played in intercollegiate tournaments regularly. I play with a Predator SP2 REVO play cue and a Mezz Dual Force break & jump cue.



Research Highlights

Script Learning with wikihow [5][6]
Nov 2019 - Present
Dialogue Sentence Semantics Resources and Evaluation
Using wikiHow, we create learning resources and evaluation benchmarks for reasoning goal-step and temporal event relations. Our training data is effective for NLU tasks involving these relations, such as intent detection. We are currently expanding our resources to multilingual and multimodal versions.
Split and Rephrase: Evaluation Benchmarks and Metrics [4]
Apr 2019 - Jun 2019
Text Simplification Resources and Evaluation
Split and Rephrase is a text simplification task to rewrite a complex sentence into several simpler ones. We show that the existing benchmark is too simplistic, developing a rule-based model using no training data which performs on par with the current state-of-the-art neural model. We then propose two new crowdsourced benchmarks with improved quality. We also provide a study on the flaws of BLEU score, and the cost-efficiency of using crowd workers to evaluate models.



Publications

[6] Intent Detection with WikiHow
Li Zhang, Qing Lyu and Chris Callison-Burch

Paper BibTeX Repo  In AACL-IJCNLP 2020.

[5] Reasoning about Goals, Steps, and Temporal Ordering with WikiHow
Li Zhang*Equal contribution, Qing Lyu*Equal contribution and Chris Callison-Burch

Paper BibTeX Repo  In EMNLP 2020.

[4] Small but Mighty: New Benchmarks for Split and Rephrase
Li Zhang, Huaiyu Zhu, Siddhartha Brahma and Yunyao Li

Paper BibTeX  In EMNLP 2020.



Work Experience

Research Intern @ IBM ResearchIBM Research
2019, 2021

I did NLP research and software development on text simplification.


Teaching AssistantUM-Penn
2016 - 2020

At Penn, I instructed CIS 530: Computational Linguistics (Winter, Fall 2020). At Michigan, I instructed EECS 595: Natural Language Processing (Fall 2018) and EECS 280: Programming and Introductory Data Structures (Winter, Fall 2016).


Summer Analyst in Technology @ Goldman SachsGoldman Sachs
2017

I performed software engineering, data analytics and machine learning.


Education

University of Pennsylvaniaupenn logo
Philadephia, PA, USA
Ph.D. Computer and Information Science; In progress

GPA: 3.89/4.00


University of Michiganumich logo
Ann Arbor, MI, USA
B.S.E. Computer Science; Class of 2018

GPA: 3.82/4.00 summa cum laude


Shenzhen Middle SchoolSMS logo
Shenzhen, China
High School Diploma; Class of 2015

GPA: 4.23/4.30


Services

Reviewer of ACL-IJCNLP 2021
Session chair of AACL-IJCNLP 2020
Co-organizer of CLUNCH in 2020, Penn's NLP seminar series
Reviewer of COLING 2020
Reviewer of Computer Speech and Language 2018