| Extractive summarization of long documents by combining global and local context W Xiao, G Carenini EMNLP-IJCNLP 2019, 2019 | 174 | 2019 |
| PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization W Xiao, I Beltagy, G Carenini, A Cohan ACL 2022, 2022 | 155 | 2022 |
| Systematically Exploring Redundancy Reduction in Summarizing Long Documents W Xiao, G Carenini AACL 2020, 2020 | 47 | 2020 |
| Do We Really Need That Many Parameters In Transformer For Extractive Summarization? Discourse Can Help! W Xiao, P Huber, G Carenini Proceedings of the First Workshop on Computational Approaches to Discourse …, 2020 | 19 | 2020 |
| Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning L Xing, W Xiao, G Carenini ACL 2021, 2021 | 17 | 2021 |
| Entity-based SpanCopy for Abstractive Summarization to Improve the Factual Consistency W Xiao, G Carenini CODI at ACL 2023, 2023 | 14 | 2023 |
| Predicting Discourse Trees from Transformer-based Neural Summarizers W Xiao, P Huber, G Carenini NAACL 2021, 2021 | 13 | 2021 |
| Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues C Li, P Huber, W Xiao, M Amblard, C Braud, G Carenini arXiv preprint arXiv:2302.05895, 2023 | 8 | 2023 |
| Chatgpt-steered editing instructor for customization of abstractive summarization W Xiao, Y Xie, G Carenini, P He arXiv preprint arXiv:2305.02483, 2023 | 7 | 2023 |
| T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP R Li, W Xiao, L Wang, H Jang, G Carenini arXiv preprint arXiv:2108.13587, 2021 | 5 | 2021 |
| W-RST: Towards a Weighted RST-style Discourse Framework P Huber, W Xiao, G Carenini arXiv preprint arXiv:2106.02658, 2021 | 5 | 2021 |
| Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization W Xiao, L Miculicich, Y Liu, P He, G Carenini arXiv preprint arXiv:2212.10819, 2022 | 3 | 2022 |
| KW-ATTN: Knowledge Infused Attention for Accurate and Interpretable Text Classification H Jang, S Bang, W Xiao, G Carenini, R Ng, Y ji Lee Proceedings of Deep Learning Inside Out (DeeLIO): The 2nd Workshop on …, 2021 | 3 | 2021 |
| PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Y Zhang, B Gao, T Liu, K Lu, W Xiong, Y Dong, B Chang, J Hu, W Xiao arXiv preprint arXiv:2406.02069, 2024 | 2 | 2024 |
| Cross-task defense: Instruction-tuning llms for content safety Y Fu, W Xiao, J Chen, J Li, E Papalexakis, A Chien, Y Dong arXiv preprint arXiv:2405.15202, 2024 | 1 | 2024 |
| Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack Y Fu, Y Li, W Xiao, C Liu, Y Dong arXiv preprint arXiv:2312.06924, 2023 | 1 | 2023 |
| Personalized Abstractive Summarization by Tri-agent Generation Pipeline W Xiao, Y Xie, G Carenini, P He arXiv preprint arXiv:2305.02483, 2023 | 1 | 2023 |
| Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization R Li, W Xiao, L Wang, G Carenini arXiv preprint arXiv:2112.05364, 2021 | 1 | 2021 |
| Proceedings of the 4th New Frontiers in Summarization Workshop Y Dong, W Xiao, L Wang, F Liu, G Carenini Proceedings of the 4th New Frontiers in Summarization Workshop, 2023 | | 2023 |
| Exploration on the synergy between discourse and neural summarizers W Xiao University of British Columbia, 2023 | | 2023 |
Giuseppe CareniniProfessor of Computer Science, University of British ColumbiaVerified email at cs.ubc.ca
