activity
20182024
most citedNeural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning

9 citations · 24 across the 6 of their papers we have counts for

collaborators

6 papers

math.HO2024★ 6 cited

AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams

Tianyi Liu, Julia Chatain, Laura Kobel-Keller +3

Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging…

cs.LG2023★ 1 cited

Taxonomy-Structured Domain Adaptation

Tianyi Liu, Zihao Xu, Hao He +3

Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nua…

cs.LG2022

Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities

Jiandian Zeng, Tianyi Liu, Jiantao Zhou

Multimodal sentiment analysis has been studied under the assumption that all modalities are available. However, such a strong assumption does not always hold in practice, and most…

cs.CV2021★ 8 cited

Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation

Tianyi Liu, Zuxuan Wu, Wenhan Xiong +2

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining.…

cs.CL2020

Regularized Attentive Capsule Network for Overlapped Relation Extraction

Tianyi Liu, Xiangyu Lin, Weijia Jia +2

Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established…

cs.CL2018★ 9 cited

Neural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning

Tianyi Liu, Xinsong Zhang, Wanhao Zhou +1

Extracting relations is critical for knowledge base completion and construction in which distant supervised methods are widely used to extract relational facts automatically with t…