Unsupervised Class-Specific Abstractive Summarization of Customer Reviews

no code implementations • ACL (ECNLP) 2021 • Thi Nhat Anh Nguyen, Mingwei Shen, Karen Hovsepian

Large-scale unsupervised abstractive summarization is sorely needed to automatically scan millions of customer reviews in today’s fast-paced e-commerce landscape.

Abstractive Text Summarization

NICE: CVPR 2023 Challenge on Zero-shot Image Captioning

no code implementations • 5 Sep 2023 • TaeHoon Kim, Pyunghwan Ahn, Sangyun Kim, Sihaeng Lee, Mark Marsden, Alessandra Sala, Seung Hwan Kim, Bohyung Han, Kyoung Mu Lee, Honglak Lee, Kyounghoon Bae, Xiangyu Wu, Yi Gao, Hailiang Zhang, Yang Yang, Weili Guo, Jianfeng Lu, Youngtaek Oh, Jae Won Cho, Dong-Jin Kim, In So Kweon, Junmo Kim, Wooyoung Kang, Won Young Jhoo, Byungseok Roh, Jonghwan Mun, Solgil Oh, Kenan Emir Ak, Gwang-Gook Lee, Yan Xu, Mingwei Shen, Kyomin Hwang, Wonsik Shin, Kamin Lee, Wonhark Park, Dongkwan Lee, Nojun Kwak, Yujin Wang, Yimu Wang, Tiancheng Gu, Xingchang Lv, Mingmao Sun

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge.

Fairness Image Captioning

A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations

1 code implementation • NAACL (maiworkshop) 2021 • Varun Nagaraj Rao, Xingjian Zhen, Karen Hovsepian, Mingwei Shen

Explainable deep learning models are advantageous in many situations.

Misspelling Detection from Noisy Product Images

1 code implementation • COLING 2020 • Varun Nagaraj Rao, Mingwei Shen

Misspellings are introduced on products either due to negligence or as an attempt to deliberately deceive stakeholders.