no code implementations • ACL 2022 • Hui Su, Weiwei Shi, Xiaoyu Shen, Zhou Xiao, Tuo ji, Jiarui Fang, Jie zhou
Large-scale pretrained language models have achieved SOTA results on NLP tasks.
no code implementations • EMNLP 2020 • Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou
In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.
no code implementations • Findings (ACL) 2022 • Le Tian, Houjin Yu, Zhou Xiao, Hui Su, Jie zhou
Prompt-based paradigm has shown its competitive performance in many NLP tasks.
no code implementations • 11 Mar 2024 • Hui Su, Zhi Tian, Xiaoyu Shen, Xunliang Cai
However, the original scaling law paper by OpenAI did not disclose the complete details necessary to derive the precise scaling law formulas, and their conclusions are only based on models containing up to 1. 5 billion parameters.
1 code implementation • 5 Dec 2022 • Hui Su, Yue Ye, Wei Hua, Lechao Cheng, Mingli Song
In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance.
no code implementations • 21 Sep 2022 • Hui Su, Xiao Zhou, Houjin Yu, Xiaoyu Shen, YuWen Chen, Zilin Zhu, Yang Yu, Jie zhou
Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks.
1 code implementation • 3 Aug 2022 • Hui Su, Yue Ye, Zhiwei Chen, Mingli Song, Lechao Cheng
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories.
no code implementations • 14 Jun 2022 • Hyoshin Park, Justice Darko, Niharika Deshpande, Venktesh Pandey, Hui Su, Masahiro Ono, Dedrick Barkely, Larkin Folsom, Derek Posselt, Steve Chien
We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another.
no code implementations • 16 Dec 2021 • Rongzhi Zhang, Yulong Gu, Xiaoyu Shen, Hui Su
We introduce time interval embedding to represent the time pattern between the item that needs to be predicted and historical click, and use it to replace the position embedding in the original transformer (called temporal transformer).
1 code implementation • 12 Aug 2021 • Jiarui Fang, Zilin Zhu, Shenggui Li, Hui Su, Yang Yu, Jie zhou, Yang You
PatrickStar uses the CPU-GPU heterogeneous memory space to store the model data.
3 code implementations • 7 Jun 2021 • Xiangyang Mou, Chenghao Yang, Mo Yu, Bingsheng Yao, Xiaoxiao Guo, Saloni Potdar, Hui Su
Recent advancements in open-domain question answering (ODQA), i. e., finding answers from large open-domain corpus like Wikipedia, have led to human-level performance on many datasets.
no code implementations • EACL 2021 • Xiangyang Mou, Mo Yu, Shiyu Chang, Yufei Feng, Li Zhang, Hui Su
This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA).
no code implementations • EACL 2021 • Ernie Chang, Xiaoyu Shen, Dawei Zhu, Vera Demberg, Hui Su
Our approach automatically augments the data available for training by (i) generating new text samples based on replacing specific values by alternative ones from the same category, (ii) generating new text samples based on GPT-2, and (iii) proposing an automatic method for pairing the new text samples with data samples.
no code implementations • 14 Nov 2020 • Zaid Bin Tariq, Arun Iyengar, Lara Marcuse, Hui Su, Bülent Yener
But these models require a considerable number of patient-specific seizures to be recorded for extracting the preictal and interictal EEG data for training a classifier.
1 code implementation • NeurIPS 2019 • Lisha Chen, Hui Su, Qiang Ji
Existing deep learning based facial landmark detection methods have achieved excellent performance.
Ranked #6 on Facial Landmark Detection on 300W
no code implementations • WS 2020 • Xiangyang Mou, Mo Yu, Bingsheng Yao, Chenghao Yang, Xiaoxiao Guo, Saloni Potdar, Hui Su
A lot of progress has been made to improve question answering (QA) in recent years, but the special problem of QA over narrative book stories has not been explored in-depth.
no code implementations • 20 Jul 2020 • Xiangyang Mou, Brandyn Sigouin, Ian Steenstra, Hui Su
Different from purely text-based dialogue state tracking, the dialogue in AVSD contains a sequence of question-answer pairs about a video and the final answer to the given question requires additional understanding of the video.
1 code implementation • ACL 2020 • Hui Su, Xiaoyu Shen, Sanqiang Zhao, Xiao Zhou, Pengwei Hu, Randy Zhong, Cheng Niu, Jie zhou
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation.
no code implementations • ACL 2020 • Xiaoyu Shen, Ernie Chang, Hui Su, Jie zhou, Dietrich Klakow
The neural attention model has achieved great success in data-to-text generation tasks.
no code implementations • 17 Jan 2020 • Jaimie Drozdal, Justin Weisz, Dakuo Wang, Gaurav Dass, Bingsheng Yao, Changruo Zhao, Michael Muller, Lin Ju, Hui Su
We explore trust in a relatively new area of data science: Automated Machine Learning (AutoML).
no code implementations • WS 2019 • Qian Li, Hui Su, Cheng Niu, Daling Wang, Zekang Li, Shi Feng, Yifei Zhang
Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.
no code implementations • IJCNLP 2019 • Xiaoyu Shen, Yang Zhao, Hui Su, Dietrich Klakow
Pointer Generators have been the de facto standard for modern summarization systems.
1 code implementation • IJCNLP 2019 • Xiaoyu Shen, Jun Suzuki, Kentaro Inui, Hui Su, Dietrich Klakow, Satoshi Sekine
As a result, the content to be described in the text cannot be explicitly controlled.
1 code implementation • ACL 2019 • Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, Jie zhou
To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network.
no code implementations • EMNLP 2018 • Hui Su, Xiaoyu Shen, Wenjie Li, Dietrich Klakow
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems.
1 code implementation • 14 May 2018 • Zhibing Zhao, Haoming Li, Junming Wang, Jeffrey Kephart, Nicholas Mattei, Hui Su, Lirong Xia
We propose a cost-effective framework for preference elicitation and aggregation under the Plackett-Luce model with features.
no code implementations • 6 Feb 2018 • Xiaoyu Shen, Hui Su, Shuzi Niu, Vera Demberg
Variational encoder-decoders (VEDs) have shown promising results in dialogue generation.
13 code implementations • IJCNLP 2017 • Yan-ran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, Shuzi Niu
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects.
no code implementations • 14 Sep 2017 • Matthew Peveler, Naveen Sundar Govindarajulu, Selmer Bringsjord, Biplav Srivastava, Kartik Talamadupula, Hui Su
These \textit{cognitive and immersive systems} (CAISs) fall squarely into the intersection of AI with HCI/HRI: such systems interact with and assist the human agents that enter them, in no small part because such systems are infused with AI able to understand and reason about these humans and their knowledge, beliefs, goals, communications, plans, etc.
no code implementations • ACL 2017 • Xiaoyu Shen, Hui Su, Yan-ran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.