Colin Lockard

Twitter: @ColinLockard

LinkedIn

GitHub


I am a researcher working on artificial intelligence and machine learning, with particular application to the understanding of human communications. My work focuses on developing methods to help computers understand and extract information from natural language sources such as newspapers and websites. I am currently an Applied Scientist on Amazon's Product Graph team.

I hold a PhD in Computer Science & Engineering from the University of Washington, where I was advised by Hannaneh Hajishirzi and additionally supervised by Xin Luna Dong. Our work on the Ceres project was the subject of Luna's keynote address at the 2020 Conference on Information and Knowledge Management (CIKM).

I also hold a BA in English from Harvard University and an MA in Interdisciplinary Computer Science from Mills College. Prior to starting my PhD, I completed a stint with the Big Data Analytics & Machine Intelligence group at NASA Langley Research Center, taught at Peking University in Beijing, and did some time in the business world.


Publications

"TCN: Table Convolutional Network for Web Table Interpretation"
Daheng Wang, Prashant Shiralkar, Colin Lockard, Binxuan Huang, Xin Luna Dong, Meng Jiang
in Proceedings of the Web Conference (WWW), 2021

"ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages"
Colin Lockard, Prashant Shiralkar, Xin Luna Dong, Hannaneh Hajishirzi
in Proceedings of the Association for Computational Linguistics (ACL), 2020
[slides]

"OpenCeres: When Open Information Extraction Meets the Semi-Structured Web"
Colin Lockard, Prashant Shiralkar, Xin Luna Dong
in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019
[slides] [Expanded SWDE dataset]

"OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference"
Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Xin Luna Dong, Andrew McCallum
in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019

"CERES: Distantly Supervised Relation Extraction from the Semi-Structured Web"
Colin Lockard, Xin Luna Dong, Arash Einolghozati, Prashant Shiralkar
in Proceedings of the VLDB Endowment (PVLDB), 2018
[slides]

"Semi-Supervised Event Extraction with Paraphrase Clusters"
James Ferguson, Colin Lockard, Daniel S. Weld, Hannaneh Hajishirzi
in Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018

"University of Washington TAC-KBP 2016 System Description"
James Ferguson, Colin Lockard, Natalie Hawkins, Stephen Soderland, Hannaneh Hajishirzi, Daniel S. Weld
in Proceedings of TAC-KBP, 2017


Tutorials

Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web, KDD 2020

Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web, ACL 2020

Web-scale Knowledge Collection, WSDM 2020


Service

I regularly serve as a reviewer or progam committee member for conferences and journals in AI and NLP, including:

Meta-Learning for NLP Workshop (ACL 2021)

KDD (2021)

AAAI (2020, 2021)

EMNLP (2019, 2020 - Outstanding Reviewer Award)

DI2KG Workshop (KDD 2019, VLDB 2020)

AKBC (2020)

IEEE Transactions on Knowledge and Data Engineering (TKDE) (2017-present)