Zhuyun Dai

Language Technologies Institute, Carnegie Mellon University



I am a Ph.D. candidate at Language Technologies Institute (LTI), Carnegie Mellon University. I am working with Professor Jamie Callan. I am in the final year, and expect to graduate in 2020 Summer.

My research interests fall in the intersection of Information Retrieval, Deep Learning, and Natural Language Processing. My Ph.D. dissertation research develops neural network solutions to improve text representation, relevance modeling, and language understanding in today's retrieval systems. It aims to combine user's search preferences and general language uses, to provide intelligent, efficient, and generally applicable solutions to retrieval. Starting recently, I also study complex-result summarization for response generatio in conversational AI systems.

I came to LTI in 2014 fall as a master student in the Master in Language Technologies (MLT) program, and started in the Ph.D. program in 2016 fall. For my master's research, I worked on the selective search project which aims to reduce the costs of searching large web-scale corpus. Prior to CMU, I completed my undergraduate study in Peking University, majoring in Computer Science.

For more information, please visit my Curriculum Vitae, and find my pulications on the publications page or Google Scholar.

Last updated: January 12, 2020.




One full paper accepted by the Web Conference 2020 (Oral Presentation).


We are happy to release code and data for our paper "Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval"


Our paper "Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrieval" was on arXiv. This is the technique I used to build the W-Index↓


My W-Index retrieval + BERT-F re-rank method is at the 2nd place on Microsoft MSMARCO passage ranking leaderboard

Email: zhuyund [at] cs [dot] cmu [dot] edu

Address: 5000 Forbes Avenue

Office: 5513 Gates Hillman Complex

Google Scholar




Honors & Awards

MS in Language Technologies

Language Technologies Institute, School of Computer Science

Carnegie Mellon University, Pittsburgh, United States

2014.08 - 2016.06

B.S. in Computer Science

Computer Science Department, School of Electronic Engineering and Computer Science

Peking University, Beijing, China

2010.09 - 2014.07

GPA: 3.77/4.0

  • 2019.06  1st Place in the Forte Woman's Leadership Power Pitch Competition

  • 2019.03  2nd Place in the 2019 CMU McGinnis Venture Competition

  • 2014.07  2014 Outstanding Graduating Student of Beijing

  • 2014.06  2014 Excellent Graduation Thesis, Peking University

  • 2013.07  The Google Anita Borg Memorial Scholarship