no code implementations • 11 Mar 2025 • Tianyu Sun, Kun Qian, Wenhong Wang
Multi-party dialogue generation presents significant challenges due to the complex interplay of multiple speakers and interwoven conversational threads.
no code implementations • 21 Feb 2025 • Yuan Tian, Daniel Lee, Fei Wu, Tung Mai, Kun Qian, Siddhartha Sahai, Tianyi Zhang, Yunyao Li
Text-to-SQL models, which parse natural language (NL) questions to executable SQL queries, are increasingly adopted in real-world applications.
2 code implementations • 8 Jan 2025 • Zijiang Yang, Meishu Song, Xin Jing, Haojie Zhang, Kun Qian, Bin Hu, Kota Tamada, Toru Takumi, Björn W. Schuller, Yoshiharu Yamamoto
The findings suggest promising directions for vocalization analysis and highlight the potential value of audible and ultrasound vocalizations in ASD detection.
no code implementations • 19 Dec 2024 • Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Naana Obeng-Marnu, Manan Dey, Mohammed Hamdy, Nayan Saxena, Ahmad Mustafa Anis, Emad A. Alghamdi, Vu Minh Chien, Da Yin, Kun Qian, Yizhi Li, Minnie Liang, An Dinh, Shrestha Mohanty, Deividas Mataciunas, Tobin South, JianGuo Zhang, Ariel N. Lee, Campbell S. Lund, Christopher Klamm, Damien Sileo, Diganta Misra, Enrico Shippole, Kevin Klyman, Lester JV Miranda, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Vipul Gupta, Vivek Sharma, Xuhui Zhou, Caiming Xiong, Luis Villa, Stella Biderman, Alex Pentland, Sara Hooker, Jad Kabbara
In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation.
no code implementations • 1 Dec 2024 • Kun Qian, Tianyu Sun, Wenhong Wang
Industrial anomaly detection (IAD) plays a crucial role in the maintenance and quality control of manufacturing processes.
no code implementations • 16 Nov 2024 • Xingyu Chen, Zihao Feng, Kun Qian, Xinyu Zhang
Radio frequency (RF) propagation modeling poses unique electromagnetic simulation challenges.
no code implementations • 15 Oct 2024 • Jiacheng Lin, Kun Qian, Haoyu Han, Nurendra Choudhary, Tianxin Wei, Zhongruo Wang, Sahika Genc, Edward W Huang, Sheng Wang, Karthik Subbian, Danai Koutra, Jimeng Sun
Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval, question answering, and classification.
1 code implementation • 23 Jul 2024 • Sabyasachi Basu, Daniel Paul-Pena, Kun Qian, C. Seshadhri, Edward W Huang, Karthik Subbian
A fundamental task in graph mining is to discover these dense subgraphs.
no code implementations • 20 Jul 2024 • Shayne Longpre, Robert Mahari, Ariel Lee, Campbell Lund, Hamidah Oderinwale, William Brannon, Nayan Saxena, Naana Obeng-Marnu, Tobin South, Cole Hunter, Kevin Klyman, Christopher Klamm, Hailey Schoelkopf, Nikhil Singh, Manuel Cherep, Ahmad Anis, An Dinh, Caroline Chitongo, Da Yin, Damien Sileo, Deividas Mataciunas, Diganta Misra, Emad Alghamdi, Enrico Shippole, JianGuo Zhang, Joanna Materzynska, Kun Qian, Kush Tiwary, Lester Miranda, Manan Dey, Minnie Liang, Mohammed Hamdy, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Shrestha Mohanty, Vipul Gupta, Vivek Sharma, Vu Minh Chien, Xuhui Zhou, Yizhi Li, Caiming Xiong, Luis Villa, Stella Biderman, HanLin Li, Daphne Ippolito, Sara Hooker, Jad Kabbara, Sandy Pentland
To our knowledge, we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora.
1 code implementation • 28 Jun 2024 • Xuanming Zhang, Anthony Diaz, Zixun Chen, Qingyang Wu, Kun Qian, Erik Voss, Zhou Yu
To bridge this gap, we introduce DECOR, a novel benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoherent sentences.
1 code implementation • 25 Jun 2024 • Kun Qian, Shunji Wan, Claudia Tang, Youzhi Wang, Xuanming Zhang, Maximillian Chen, Zhou Yu
As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem.
no code implementations • 21 Jun 2024 • Yi Chang, Zhao Ren, Zhonghao Zhao, Thanh Tam Nguyen, Kun Qian, Tanja Schultz, Björn W. Schuller
Speech emotion recognition (SER) plays a crucial role in human-computer interaction.
no code implementations • 19 Jun 2024 • Wenjie Li, Tianyu Sun, Kun Qian, Wenhong Wang
The advent of large language models (LLMs) has significantly advanced various fields, including natural language processing and automated dialogue systems.
1 code implementation • 6 Jun 2024 • Xiou Ge, Ali Mousavi, Edouard Grave, Armand Joulin, Kun Qian, Benjamin Han, Mostafa Arefiyan, Yunyao Li
It is thus essential to design effective methods to both update obsolete knowledge and induce new knowledge into LLMs.
no code implementations • 18 May 2024 • Kun Qian, Mohamed Kheir
The main objective of this paper is to investigate the feasibility of employing Physics-Informed Neural Networks (PINNs) techniques, in particular KolmogorovArnold Networks (KANs), for facilitating Electromagnetic Interference (EMI) simulations.
no code implementations • 4 Mar 2024 • Chen Xu, Tian Lan, Changlong Yu, Wei Wang, Jun Gao, Yu Ji, Qunxi Dong, Kun Qian, Piji Li, Wei Bi, Bin Hu
Constrained decoding approaches aim to control the meaning or style of text generated by a Pre-trained Language Model (PLM) using specific target words during inference.
no code implementations • 2 Feb 2024 • Yi Chang, Zhao Ren, Zixing Zhang, Xin Jing, Kun Qian, Xi Shao, Bin Hu, Tanja Schultz, Björn W. Schuller
Speech contains rich information on the emotions of humans, and Speech Emotion Recognition (SER) has been an important topic in the area of human-computer interaction.
1 code implementation • 28 Nov 2023 • Xiaoyu Du, Kun Qian, Yunshan Ma, Xinguang Xiang
In this paper, we propose a novel approach EBRec, short of Enhanced Bundle Recommendation, which incorporates two enhanced modules to explore inherent item-level bundle representations.
no code implementations • 26 Oct 2023 • Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyi, Samira Khorshidi, Fei Wu, Ihab F. Ilyas, Yunyao Li
Detecting factual errors in textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions.
no code implementations • 7 Oct 2023 • Zixuan Liu, Gaurush Hiranandani, Kun Qian, Eddie W. Huang, Yi Xu, Belinda Zeng, Karthik Subbian, Sheng Wang
ForeSeer transfers reviews from similar products on a large product graph and exploits these reviews to predict aspects that might emerge in future reviews.
no code implementations • 28 Sep 2023 • Kun Qian, Yuanyuan Wang, Peter Jung, Yilei Shi, Xiao Xiang Zhu
Deep neural networks based on unrolled iterative algorithms have achieved remarkable success in sparse reconstruction applications, such as synthetic aperture radar (SAR) tomographic inversion (TomoSAR).
no code implementations • 16 Aug 2023 • JianGuo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models.
1 code implementation • 19 Jul 2023 • JianGuo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong
Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness.
no code implementations • 23 May 2023 • Kun Qian, Yuanyuan Wang, Peter Jung, Yilei Shi, Xiao Xiang Zhu
An emerging technique known as deep unrolling provided a good combination of the descriptive ability of neural networks, explainable, and computational efficiency for BPDN.
no code implementations • 29 Apr 2023 • Bin Du, Kun Qian, Christian Claudel, Dengfeng Sun
This paper proposes to leverage the emerging~learning techniques and devise a multi-agent online source {seeking} algorithm under unknown environment.
no code implementations • 11 Apr 2023 • Kun Qian, Ryan Shea, Yu Li, Luke Kutszik Fryer, Zhou Yu
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing.
no code implementations • 12 Feb 2023 • Derek Chen, Kun Qian, Zhou Yu
Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks.
1 code implementation • 23 Jan 2023 • Zhao Ren, Yi Chang, Thanh Tam Nguyen, Yang Tan, Kun Qian, Björn W. Schuller
This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis.
1 code implementation • 30 Nov 2022 • Xiao Yu, Qingyang Wu, Kun Qian, Zhou Yu
In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics.
no code implementations • 22 Nov 2022 • Jie Zhang, Yihui Zhao, Tianzhe Bao, Zhenhong Li, Kun Qian, Alejandro F. Frangi, Sheng Quan Xie, Zhi-Qiang Zhang
The salient advantages of the proposed framework are twofold: 1) For the generic model, physics-based domain knowledge is embedded into the loss function of the data-driven model as soft constraints to penalise/regularise the data-driven model.
1 code implementation • 26 Oct 2022 • Yi Chang, Zhao Ren, Thanh Tam Nguyen, Kun Qian, Björn W. Schuller
Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance compared to models with speech samples only and those using classic transfer learning strategies.
no code implementations • 25 May 2022 • Yukun Huang, Kun Qian, Zhou Yu
So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data.
no code implementations • 4 Mar 2022 • Yu-Xin Jin, Jun-Jie Hu, Qi Li, Zhi-Cheng Luo, Fang-Yan Zhang, Hao Tang, Kun Qian, Xian-Min Jin
New COVID-19 epidemic strains like Delta and Omicron with increased transmissibility and pathogenicity emerge and spread across the whole world rapidly while causing high mortality during the pandemic period.
no code implementations • 2 Mar 2022 • Shuo Liu, Adria Mallol-Ragolta, Emilia Parada-Cabeleiro, Kun Qian, Xin Jing, Alexander Kathan, Bin Hu, Bjoern W. Schuller
Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which is an expensive and time consuming task.
no code implementations • 15 Dec 2021 • Lei Zuo, Kun Qian, Bowen Yang, Zhou Yu
A commonly observed problem of the state-of-the-art natural language technologies, such as Amazon Alexa and Apple Siri, is that their services do not extend to most developing countries' citizens due to language barriers.
no code implementations • NAACL 2022 • Kun Qian, Ahmad Beirami, Satwik Kottur, Shahin Shayandeh, Paul Crook, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar
We find that training on our augmented dialog data improves the model's ability to deal with ambiguous scenarios, without sacrificing performance on unmodified turns.
no code implementations • 8 Dec 2021 • Kun Qian, Yuanyuan Wang, Yilei Shi, Xiao Xiang Zhu
This superior performance comes at the cost of extra computational burdens, because of the sparse reconstruction, which cannot be solved analytically and we need to employ computationally expensive iterative solvers.
no code implementations • 29 Sep 2021 • Mengji Zhang, Yingce Xia, Nian Wu, Kun Qian, Jianyang Zeng
Manually interpreting the MS/MS spectrum into the molecules (i. e., the simplified molecular-input line-entry system, SMILES) is often costly and cumbersome, mainly due to the synthesis and labeling of isotopes and the requirement of expert knowledge.
1 code implementation • CVPR 2021 • Kun Qian, Shilin Zhu, Xinyu Zhang, Li Erran Li
Vehicle detection with visual sensors like lidar and camera is one of the critical functions enabling autonomous driving.
no code implementations • SIGDIAL (ACL) 2021 • Kun Qian, Ahmad Beirami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar
In this work, we identify an overlooked issue with dialog state annotation inconsistencies in the dataset, where a slot type is tagged inconsistently across similar dialogs leading to confusion for DST modeling.
no code implementations • 6 Apr 2021 • Kun Qian, Wei Wei, Zhou Yu
The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process.
no code implementations • 8 Dec 2020 • Kun Qian, Bjorn W. Schuller, Yoshiharu Yamamoto
Computer audition (CA) has been demonstrated to be efficient in healthcare domains for speech-affecting disorders (e. g., autism spectrum, depression, or Parkinson's disease) and body sound-affecting abnormalities (e. g., abnormal bowel sounds, heart murmurs, or snore sounds).
no code implementations • 24 Nov 2020 • Kun Qian, Yuanyuan Wang, Xiaoxiang Zhu
Existing SAR tomography (TomoSAR) algorithms are mostly based on an inversion of the SAR imaging model, which are often computationally expensive.
no code implementations • 24 Nov 2020 • Chuhua Xian, Kun Qian, Zitian Zhang, Charlie C. L. Wang
Next, we propose a step-wise fusion strategy to restore the HR depth map.
1 code implementation • EMNLP 2020 • Kun Qian, Poornima Chozhiyath Raman, Yunyao Li, Lucian Popa
Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation.
no code implementations • 14 Oct 2020 • Qingyang Wu, Zhenzhong Lan, Kun Qian, Jing Gu, Alborz Geramifard, Zhou Yu
Transformers have reached remarkable success in sequence modeling.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katsis, Ban Kawas, Prithviraj Sen
Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable.
no code implementations • 12 Jul 2020 • Liang Zhang, Johann Li, Ping Li, Xiaoyuan Lu, Peiyi Shen, Guangming Zhu, Syed Afaq Shah, Mohammed Bennarmoun, Kun Qian, Björn W. Schuller
To the best of our knowledge, MeDaS is the first open-source platform proving a collaborative and interactive service for researchers from a medical background easily using DL related toolkits, and at the same time for scientists or engineers from information sciences to understand the medical knowledge side.
no code implementations • WS 2020 • Nikita Bhutani, Xinyi Zheng, Kun Qian, Yunyao Li, H. Jagadish
Knowledge-based question answering (KB{\_}QA) has long focused on simple questions that can be answered from a single knowledge source, a manually curated or an automatically extracted KB.
no code implementations • 11 May 2020 • Tomoya Koike, Kun Qian, Björn W. Schuller, Yoshiharu Yamamoto
To the best of our knowledge, it is the first public toolkit assembling a series of state-of-the-art deep learning technologies.
no code implementations • 30 Apr 2020 • Jing Han, Kun Qian, Meishu Song, Zijiang Yang, Zhao Ren, Shuo Liu, Juan Liu, Huaiyuan Zheng, Wei Ji, Tomoya Koike, Xiao Li, Zixing Zhang, Yoshiharu Yamamoto, Björn W. Schuller
In particular, by analysing speech recordings from these patients, we construct audio-only-based models to automatically categorise the health state of patients from four aspects, including the severity of illness, sleep quality, fatigue, and anxiety.
no code implementations • 24 Mar 2020 • Björn W. Schuller, Dagmar M. Schuller, Kun Qian, Juan Liu, Huaiyuan Zheng, Xiao Li
We come to the conclusion that CA appears ready for implementation of (pre-)diagnosis and monitoring tools, and more generally provides rich and significant, yet so far untapped potential in the fight against COVID-19 spread.
3 code implementations • CVPR 2020 • Abduallah Mohamed, Kun Qian, Mohamed Elhoseiny, Christian Claudel
Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans.
Ranked #3 on
Trajectory Prediction
on ETH
1 code implementation • 25 Nov 2019 • Yu Li, Kun Qian, Weiyan Shi, Zhou Yu
End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task.
1 code implementation • IJCNLP 2019 • Weiyan Shi, Kun Qian, Xuewei Wang, Zhou Yu
We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly.
1 code implementation • 23 Aug 2019 • Kun Qian, Abduallah Mohamed, Christian Claudel
Flash floods in urban areas occur with increasing frequency.
no code implementations • 14 Aug 2019 • Zhiming Li, Qing Wu, Kun Qian
Specifically, in terms of BLEU-4 and Word Error Rate (WER), our performance has reached 94. 50% and 2. 65% on the redundant test set; 92. 30% and 3. 48% on the purified test set.
no code implementations • ACL 2019 • Jungo Kasai, Kun Qian, Sairam Gurajada, Yunyao Li, Lucian Popa
Recent adaptation of deep learning methods for ER mitigates the need for dataset-specific feature engineering by constructing distributed representations of entity records.
1 code implementation • ACL 2019 • Kun Qian, Zhou Yu
We train a dialog system model using multiple rich-resource single-domain dialog data by applying the model-agnostic meta-learning algorithm to dialog domain.
no code implementations • 29 Mar 2019 • Zixing Zhang, Jing Han, Kun Qian, Christoph Janott, Yanan Guo, Bjoern Schuller
One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data.
no code implementations • 29 Jan 2019 • Phokion G. Kolaitis, Lucian Popa, Kun Qian
In this paper, we carry out a systematic complexity-theoretic investigation of the following rule selection problem: given a set of rules specified by Horn formulas, and a pair of an input database and an output database, find a subset of the rules that minimizes the total error, that is, the number of false positive and false negative errors arising from the selected rules.
no code implementations • 28 Oct 2018 • Kun Qian, Jun Zhou, Fengchao Xiong, Huixin Zhou, Juan Du
Target tracking in hyperspectral videos is a new research topic.
no code implementations • COLING 2018 • Nikita Bhutani, Kun Qian, Yunyao Li, H. V. Jagadish, Hern, Mauricio ez, Mitesh Vasa
We show that programs for mapping entity mentions to their structures can be automatically generated using human-comprehensible labels.
no code implementations • 27 Jul 2017 • Zixing Zhang, Ding Liu, Jing Han, Kun Qian, Björn Schuller
Extensive evaluation on a large-size acoustic event database is performed, and the empirical results demonstrate that the learnt audio sequence representation yields a significant performance improvement by a large margin compared with other state-of-the-art hand-crafted sequence features for AEC.