13 citations · 14 across the 7 of their papers we have counts for
8 papers
Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval
Junghyun Min, Huseyin Uzunalioglu, Mohamed Trabelsi
Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing human roles…
Using Prosody to Predict Syntactic Structure
Junghyun Min, Alex Warstadt, Tamar I. Regev +2
While it is well-established that prosody carries crucial cues for syntactic structure, the degree and nature of correspondence between these two domains remains contested. We inve…
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…
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…
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…
Syntactic Data Augmentation Increases Robustness to Inference Heuristics
Junghyun Min, R. Thomas McCoy, Dipanjan Das +2
Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of…
BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance
R. Thomas McCoy, Junghyun Min, Tal Linzen
If the same neural network architecture is trained multiple times on the same dataset, will it make similar linguistic generalizations across runs? To study this question, we fine-…