4 papers
Structured Language Generation Model: Loss Calibration and Formatted Decoding for Robust Structure Prediction and Knowledge Retrieval
Minho Lee, Junghyun Min, Yerang Kim +2
Modern generative pre-trained language models excel at open-ended text generation, yet continue to underperform on structure-related tasks such as NER, relation extraction, and sem…
When Does Meaning Backfire? Investigating the Role of AMRs in NLI
Junghyun Min, Xiulin Yang, Shira Wein
Natural Language Inference (NLI) relies heavily on adequately parsing the semantic content of the premise and hypothesis. In this work, we investigate whether adding semantic infor…
Building UD Cairo for Old English in the Classroom
Lauren Levine, Junghyun Min, Amir Zeldes
In this paper we present a sample treebank for Old English based on the UD Cairo sentences, collected and annotated as part of a classroom curriculum in Historical Linguistics. To…
Punctuation Restoration Improves Structure Understanding Without Supervision
Junghyun Min, Minho Lee, Woochul Lee +1
Unsupervised learning objectives like autoregressive and masked language modeling constitute a significant part in producing pre-trained representations that perform various downst…