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