papers

Publications (15)

cs.CL2021

Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring

Linzi Xing, Giuseppe Carenini

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence…

cs.LG2025

Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs

Morgan Lindsay Heisler, Linzi Xing, Ge Shi +7

Huawei Cloud users leverage LoRA (Low-Rank Adaptation) as an efficient and scalable method to fine-tune and customize large language models (LLMs) for application-specific needs. H…

cs.CL2019

Evaluating Topic Quality with Posterior Variability

Linzi Xing, Michael J. Paul, Giuseppe Carenini

Probabilistic topic models such as latent Dirichlet allocation (LDA) are popularly used with Bayesian inference methods such as Gibbs sampling to learn posterior distributions over…

math.OC2024

Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process

Zhenan Fan, Bissan Ghaddar, Xinglu Wang +3

The rapid advancement of artificial intelligence (AI) techniques has opened up new opportunities to revolutionize various fields, including operations research (OR). This survey pa…

cs.CL2020

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

Xiaolei Huang, Linzi Xing, Franck Dernoncourt +1

Existing research on fairness evaluation of document classification models mainly uses synthetic monolingual data without ground truth for author demographic attributes. In this wo…

cs.CL2022

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

Raymond Li, Wen Xiao, Linzi Xing +3

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why an…

cs.CL2023

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

Linzi Xing, Brad Hackinen, Giuseppe Carenini

U.S. Federal Regulators receive over one million comment letters each year from businesses, interest groups, and members of the public, all advocating for changes to proposed regul…

cs.CL2023

Diversity-Aware Coherence Loss for Improving Neural Topic Models

Raymond Li, Felipe González-Pizarro, Linzi Xing +2

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, i…

cs.MM2023

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

Linzi Xing, Quan Tran, Fabian Caba +5

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal…

cs.CL2020

Improving Context Modeling in Neural Topic Segmentation

Linzi Xing, Brad Hackinen, Giuseppe Carenini +1

Topic segmentation is critical in key NLP tasks and recent works favor highly effective neural supervised approaches. However, current neural solutions are arguably limited in how…

cs.AI2026

DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing

Daesik Jang, Morgan Lindsay Heisler, Linzi Xing +5

Automatically generating and iteratively editing academic slide decks requires more than document summarization. It demands faithful content selection, coherent slide organization,…

cs.CL2021

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Linzi Xing, Wen Xiao, Giuseppe Carenini

In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data wit…

cs.CL2022

Improving Topic Segmentation by Injecting Discourse Dependencies

Linzi Xing, Patrick Huber, Giuseppe Carenini

Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sam…

cs.DC2025

Efficiently Serving Large Multimodal Models Using EPD Disaggregation

Gursimran Singh, Xinglu Wang, Yifan Hu +9

Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stag…

cs.CL2021

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

Patrick Huber, Linzi Xing, Giuseppe Carenini

RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its im…