22 citations · 35 across the 11 of their papers we have counts for
4 papers · 1 filter
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…
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…
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…
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…