89 citations · 279 across the 27 of their papers we have counts for
7 papers · 1 filter
Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
Zhihui Xie, Handong Zhao, Tong Yu +1
Large pretrained multilingual language models (ML-LMs) have shown remarkable capabilities of zero-shot cross-lingual transfer, without direct cross-lingual supervision. While these…
InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
Junda Wu, Tong Yu, Rui Wang +6
Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of…
Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning
Kaige Xie, Tong Yu, Haoliang Wang +6
In real-world scenarios, labeled samples for dialogue summarization are usually limited (i.e., few-shot) due to high annotation costs for high-quality dialogue summaries. To effici…
Unified Pretraining Framework for Document Understanding
Jiuxiang Gu, Jason Kuen, Vlad I. Morariu +5
Document intelligence automates the extraction of information from documents and supports many business applications. Recent self-supervised learning methods on large-scale unlabel…
Edge: Enriching Knowledge Graph Embeddings with External Text
Saed Rezayi, Handong Zhao, Sungchul Kim +3
Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods. While there is an abundance of textual information throughout the…
Learning Contextualized Knowledge Structures for Commonsense Reasoning
Jun Yan, Mrigank Raman, Aaron Chan +6
Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/…
Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
Mrigank Raman, Aaron Chan, Siddhant Agarwal +7
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation. By using attention over…