no code implementations • EMNLP 2021 • Jeonghwan Kim, Giwon Hong, Kyung-Min Kim, Junmo Kang, Sung-Hyon Myaeng
Our work rigorously tests state-of-the-art models on DROP, a numerical MRC dataset, to see if they can handle passages that contain out-of-range numbers.
no code implementations • EACL (HCINLP) 2021 • Jeonghwan Kim, Junmo Kang, Suwon Shin, Sung-Hyon Myaeng
Customer reviews are useful in providing an indirect, secondhand experience of a product.
no code implementations • Findings (NAACL) 2022 • Jeonghwan Kim, Junmo Kang, Kyung-Min Kim, Giwon Hong, Sung-Hyon Myaeng
Numerical reasoning over text is a challenging subtask in question answering (QA) that requires both the understanding of texts and numbers.
no code implementations • 29 Sep 2023 • Junmo Kang, Hongyin Luo, Yada Zhu, James Glass, David Cox, Alan Ritter, Rogerio Feris, Leonid Karlinsky
Recent works have demonstrated the effectiveness of self-alignment in which a large language model is, by itself, aligned to follow general instructions through the automatic generation of instructional data using a handful of human-written seeds.
1 code implementation • 23 May 2023 • Fan Bai, Junmo Kang, Gabriel Stanovsky, Dayne Freitag, Alan Ritter
We use this collection of annotated tables to evaluate the ability of open-source and API-based language models to extract information from tables covering diverse domains and data formats.
Ranked #1 on Attribute Extraction on SWDE
1 code implementation • 2 May 2023 • Giwon Hong, Jeonghwan Kim, Junmo Kang, Sung-Hyon Myaeng, Joyce Jiyoung Whang
Most existing retrieval-augmented language models (LMs) assume a naive dichotomy within a retrieved document set: query-relevance and irrelevance.
no code implementations • 2 May 2023 • Junmo Kang, Wei Xu, Alan Ritter
Fine-tuning large models is highly effective, however, inference can be expensive and produces carbon emissions.
no code implementations • 13 Oct 2021 • Junmo Kang, Suwon Shin, Jeonghwan Kim, Jaeyoung Jo, Sung-Hyon Myaeng
Moreover, we evaluate an initial approach to the problem that has not succeeded in maintaining the accuracy of the model while showing a promising compute efficiency by thoroughly investigating the necessity of the generator module of ELECTRA.
no code implementations • EMNLP 2021 • Kyoung-Rok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Heecheol Seo
The semantic matching capabilities of neural information retrieval can ameliorate synonymy and polysemy problems of symbolic approaches.
no code implementations • EMNLP 2021 • Junmo Kang, Jeonghwan Kim, Suwon Shin, Sung-Hyon Myaeng
Tag recommendation relies on either a ranking function for top-$k$ tags or an autoregressive generation method.
no code implementations • COLING 2020 • Giwon Hong, Junmo Kang, Doyeon Lim, Sung-Hyon Myaeng
Advances in Question Answering (QA) research require additional datasets for new domains, languages, and types of questions, as well as for performance increases.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Junmo Kang, Giwon Hong, Haritz Puerto San Roman, Sung-Hyon Myaeng
Unsupervised question answering (UQA) has been proposed to avoid the high cost of creating high-quality datasets for QA.
no code implementations • WS 2019 • Junmo Kang, Haritz Puerto San Roman, Sung-Hyon Myaeng
Owing to an increased recall of deciding the interrogative words to be used for the generated questions, the proposed model achieves new state-of-the-art results on the task of QG in SQuAD, improving from 46. 58 to 47. 69 in BLEU-1, 17. 55 to 18. 53 in BLEU-4, 21. 24 to 22. 33 in METEOR, and from 44. 53 to 46. 94 in ROUGE-L.