Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Giuseppe Carenini

Giuseppe Carenini

University of British Columbia

Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models


Apr 08, 2022
Patrick Huber, Giuseppe Carenini

* In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 
* 9 pages 

  Access Paper or Ask Questions

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


Dec 12, 2021
Patrick Huber, Linzi Xing, Giuseppe Carenini

* AAAI 2022 

  Access Paper or Ask Questions

Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization


Dec 10, 2021
Raymond Li, Wen Xiao, Lanjun Wang, Giuseppe Carenini


  Access Paper or Ask Questions

PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization


Oct 16, 2021
Wen Xiao, Iz Beltagy, Giuseppe Carenini, Arman Cohan


  Access Paper or Ask Questions

T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP


Aug 31, 2021
Raymond Li, Wen Xiao, Lanjun Wang, Hyeju Jang, Giuseppe Carenini

* 10 pages, 4 figures, accepted to EMNLP 2021 System Demonstration 

  Access Paper or Ask Questions

ConVIScope: Visual Analytics for Exploring Patient Conversations


Aug 30, 2021
Raymond Li, Enamul Hoque, Giuseppe Carenini, Richard Lester, Raymond Chau

* 5 pages, 3 figures, accepted as short paper at IEEE VIS 2021 

  Access Paper or Ask Questions

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring


Jun 12, 2021
Linzi Xing, Giuseppe Carenini

* Long paper accepted at SIGDIAL 2021 

  Access Paper or Ask Questions

W-RST: Towards a Weighted RST-style Discourse Framework


Jun 04, 2021
Patrick Huber, Wen Xiao, Giuseppe Carenini

* 9 pages, Accepted at ACL 2021 

  Access Paper or Ask Questions

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning


May 29, 2021
Linzi Xing, Wen Xiao, Giuseppe Carenini

* Accepted at ACL-IJCNLP 2021 main conference (short paper) 

  Access Paper or Ask Questions

Predicting Discourse Trees from Transformer-based Neural Summarizers


Apr 14, 2021
Wen Xiao, Patrick Huber, Giuseppe Carenini

* 14 pages, accepted by NAACL 2021 

  Access Paper or Ask Questions

Unsupervised Learning of Discourse Structures using a Tree Autoencoder


Dec 17, 2020
Patrick Huber, Giuseppe Carenini

* Accepted to AAAI 2021, 7 pages 

  Access Paper or Ask Questions

Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help !


Dec 03, 2020
Wen Xiao, Patrick Huber, Giuseppe Carenini

* In the Proceeding of 1st Workshop on Computational Approaches to Discourse (CODI) at EMNLP 2020. 11 pages 

  Access Paper or Ask Questions

Systematically Exploring Redundancy Reduction in Summarizing Long Documents


Nov 30, 2020
Wen Xiao, Giuseppe Carenini

* 13 pages. Accepted at AACL 2020 

  Access Paper or Ask Questions

An Improved Attention for Visual Question Answering


Nov 07, 2020
Tanzila Rahman, Shih-Han Chou, Leonid Sigal, Giuseppe Carenini

* 8 pages 

  Access Paper or Ask Questions

Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining


Nov 06, 2020
Grigorii Guz, Patrick Huber, Giuseppe Carenini

* 10 pages, 1 figure, COLING 2020 

  Access Paper or Ask Questions

From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation


Nov 05, 2020
Patrick Huber, Giuseppe Carenini

* In Proceedings of the 28 International Conference on Computational Linguistics (COLING). 10 pages 

  Access Paper or Ask Questions

MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision


Nov 05, 2020
Patrick Huber, Giuseppe Carenini

* In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 9 pages 

  Access Paper or Ask Questions

Improving Context Modeling in Neural Topic Segmentation


Oct 07, 2020
Linzi Xing, Brad Hackinen, Giuseppe Carenini, Francesco Trebbi

* Accepted at AACL-IJCNLP 2020 

  Access Paper or Ask Questions

Neural RST-based Evaluation of Discourse Coherence


Sep 30, 2020
Grigorii Guz, Peyman Bateni, Darius Muglich, Giuseppe Carenini

* 8 pages, 5 figures, to be published in AACL 2020 

  Access Paper or Ask Questions

Exploratory Analysis of COVID-19 Related Tweets in North America to Inform Public Health Institutes


Jul 05, 2020
Hyeju Jang, Emily Rempel, Giuseppe Carenini, Naveed Janjua


  Access Paper or Ask Questions

Predicting Discourse Structure using Distant Supervision from Sentiment


Oct 30, 2019
Patrick Huber, Giuseppe Carenini

* Accepted to EMNLP 2019, 9 pages 

  Access Paper or Ask Questions

Extractive Summarization of Long Documents by Combining Global and Local Context


Sep 17, 2019
Wen Xiao, Giuseppe Carenini

* 12 pages (with appendix), accepted at EMNLP-IJCNLP 2019 

  Access Paper or Ask Questions

Evaluating Topic Quality with Posterior Variability


Sep 15, 2019
Linzi Xing, Michael J. Paul, Giuseppe Carenini

* 8 pages 

  Access Paper or Ask Questions

Topic Segmentation and Labeling in Asynchronous Conversations


Feb 04, 2014
Shafiq Rayhan Joty, Giuseppe Carenini, Raymond T Ng

* Journal Of Artificial Intelligence Research, Volume 47, pages 521-573, 2013 

  Access Paper or Ask Questions