Linzi Xing

Ph.D. Candidate, University of British Columbia

Department of Computer Science

ICICS x460

lzxing [AT] cs.ubc.ca

About

I am a final year Ph.D. candidate in the NLP group at the University of British Columbia (UBC) supervised by Prof. Giuseppe Carenini. I received my M.S. in Computer Science from University of Colorado Boulder where I worked with Dr. Michael J. Paul, and completed my B.S. in Management Information System at Soochow University.

My primary research interests lie in the area of natural language processing (NLP) and machine learning (ML), with a focus on designing and implementing computational models to better understand natural language in various forms. In particular, my research experience during my master's and Ph.D. journey spans such domains:

News

Education

University of British Columbia (UBC)Sept. 2018 - Present

Ph.D. in Computer Science (NLP)

Supervisor: Prof. Giuseppe Carenini

University of Colorado BoulderAug. 2016 - May. 2018

M.S. in Computer Science

Supervisor: Dr. Michael J. Paul

Soochow UniversitySept. 2012 - June. 2016

B.S. in Management Information System

GPA: 3.7/4.0 (Rank: 1/40)

Publications

Most recent publications on Google Scholar.
indicates equal contribution.

Towards Human-aligned Evaluation for Linear Programming Word Problems

Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou and Yong Zhang

In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024

Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation

Linzi Xing, Quan Hung Tran, Fabian Caba Heilbron, Franck Dernoncourt, David Seunghyun Yoon, Zhaowen Wang, Trung Bui, and Giuseppe Carenini

In Proceedings of the 30th International Conference on Multimedia Modeling (MMM 2024). 2024

TeX2Solver: a Hierarchical Semantic Parsing of TeX Document into Code for an Assistive Optimization Modeling Application

Rindra Ramamonjison, Timothy Yu, Linzi Xing, Mahdi Mostajabdaveh, Xiaorui Li, Xiaojin Fu, Xiongwei Han, Yuanzhe Chen, Ren Li, Kun Mao, and Yong Zhang

In Proceedings of the 61st Annual Meeting of Association for Computational Linguistics (ACL 2023: Demo). 2023

Diversity-Aware Coherence Loss for Improving Neural Topic Models

Raymond Li, Felipe Gonzalez-Pizarro, Linzi Xing, Gabriel Murray and Giuseppe Carenini

In Proceedings of the 61st Annual Meeting of Association for Computational Linguistics (ACL 2023: Short). 2023

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, and Giuseppe Carenin

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022). 2022

Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation

Patrick Huber, Linzi Xing, and Giuseppe Carenini

In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-22). 2022

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Linzi Xing, Wen Xiao, and Giuseppe Carenini.

In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021: Short). 2021

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

Linzi Xing, and Giuseppe Carenini

In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2021). 2021

Improving Context Modeling in Neural Topic Segmentation

Linzi Xing, Brad Hackinen, Giuseppe Carenini, and Francesco Trebbi

In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL 2020). 2020

Evaluating Topic Quality with Posterior Variability

Linzi Xing, Michael J. Paul, and Giuseppe Carenini

In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019: Short). 2019

Diagnosing and improving topic models by analyzing posterior variability

Linzi Xing, and Michael J. Paul

In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18). 2018.

Towards Human-aligned Evaluation for Linear Programming Word Problems

Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou and Yong Zhang

In Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024

Multi-Modal Video Topic Segmentation with Dual-Contrastive Domain Adaptation

Linzi Xing, Quan Hung Tran, Fabian Caba Heilbron, Franck Dernoncourt, David Seunghyun Yoon, Zhaowen Wang, Trung Bui, and Giuseppe Carenini

In Proceedings of the 30th International Conference on Multimedia Modeling (MMM 2024). 2024

Tracing Influence at Scale: A Contrastive Learning Approach to Linking Public Comments and Regulator Responses

Linzi Xing, Brad Hackinen, and Giuseppe Carenini

In Proceedings of the 5th Natural Legal Language Processing Worksho (NLLP 2023). 2023

TeX2Solver: a Hierarchical Semantic Parsing of TeX Document into Code for an Assistive Optimization Modeling Application

Rindra Ramamonjison, Timothy Yu, Linzi Xing, Mahdi Mostajabdaveh, Xiaorui Li, Xiaojin Fu, Xiongwei Han, Yuanzhe Chen, Ren Li, Kun Mao, and Yong Zhang

In Proceedings of the 61st Annual Meeting of Association for Computational Linguistics (ACL 2023: Demo). 2023

Diversity-Aware Coherence Loss for Improving Neural Topic Models

Raymond Li, Felipe Gonzalez-Pizarro, Linzi Xing, Gabriel Murray and Giuseppe Carenini

In Proceedings of the 61st Annual Meeting of Association for Computational Linguistics (ACL 2023: Short). 2023

Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation

Raymond Li, Wen Xiao, Linzi Xing, Lanjun Wang, Gabriel Murray, and Giuseppe Carenin

In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022). 2022

Improving Topic Segmentation by Injecting Discourse Dependencies

Linzi Xing, Patrick Huber, and Giuseppe Carenini

In Proceedings of the 3rd Workshop on Computational Approaches to Discourse (CODI 2022). 2022

Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation

Patrick Huber, Linzi Xing, and Giuseppe Carenini

In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-22). 2022

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Linzi Xing, Wen Xiao, and Giuseppe Carenini.

In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021: Short). 2021

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

Linzi Xing, and Giuseppe Carenini

In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2021). 2021

Improving Context Modeling in Neural Topic Segmentation

Linzi Xing, Brad Hackinen, Giuseppe Carenini, and Francesco Trebbi

In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL 2020). 2020

Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition

Xiaolei Huang, Linzi Xing, Franck Dernoncourt, and Michael J. Paul

In Proceedings of the 12th Language Resources and Evaluation Conference (LREC 2020). 2020

Evaluating Topic Quality with Posterior Variability

Linzi Xing, Michael J. Paul, and Giuseppe Carenini

In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019: Short). 2019

Diagnosing and improving topic models by analyzing posterior variability

Linzi Xing, and Michael J. Paul

In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18). 2018.

Exploring Timelines of Confirmed Suicide Incidents through Social Media

Xiaolei Huang, Linzi Xing, Jed R. Brubaker, and Michael J. Paul

In Proceedings of the 5th IEEE International Conference on Healthcare Informatics (ICHI 2017). 2017

Incorporating Metadata into Content-Based User Embeddings

Linzi Xing, and Michael J. Paul

In Proceedings of the 3rd Workshop on Noisy User-generated Text (WNUT 2017). 2017

Vitæ

Resume [for academia] in PDF (last update: 2023.07.30).

Resume [for industry] in PDF (last update: 2023.07.30).