activity
20192023
most citedImproving Conditioning in Context-Aware Sequence to Sequence Models

9 citations · 21 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL20232 cited

Continual Event Extraction with Semantic Confusion Rectification

Zitao Wang, Xinyi Wang, Wei Hu

We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting. We observe that the semantic confusion on event types s…

cs.CV20231 cited

DANAA: Towards transferable attacks with double adversarial neuron attribution

Zhibo Jin, Zhiyu Zhu, Xinyi Wang +3

While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attack…

cs.CL20233 cited

mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations

Jonas Pfeiffer, Francesco Piccinno, Massimo Nicosia +3

Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings.…

cs.CL20232 cited

Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction

Xinyi Wang, Zitao Wang, Wei Hu

Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic…

cs.CL20222 cited

Enhancing Document-level Relation Extraction by Entity Knowledge Injection

Xinyi Wang, Zitao Wang, Weijian Sun +1

Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document. It needs complex reasoning skills to synthesize various knowl…

cs.CL2021

Efficient Test Time Adapter Ensembling for Low-resource Language Varieties

Xinyi Wang, Yulia Tsvetkov, Sebastian Ruder +1

Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate…