1 code implementation • ACL (CASE) 2021 • Fiona Anting Tan, Sujatha Das Gollapalli, See-Kiong Ng
Event Sentence Coreference Identification (ESCI) aims to cluster event sentences that refer to the same event together for information extraction.
no code implementations • NAACL (CLPsych) 2021 • Sujatha Das Gollapalli, Guilherme Augusto Zagatti, See-Kiong Ng
We describe our system for identifying users at-risk for suicide based on their tweets developed for the CLPsych 2021 Shared Task.
no code implementations • COLING 2022 • Sujatha Das Gollapalli, See-Kiong Ng
Indeed, QG models continue to be evaluated using traditional measures such as BLEU, METEOR, and ROUGE scores which were designed for other text generation problems.
1 code implementation • EMNLP (CINLP) 2021 • Fiona Anting Tan, Devamanyu Hazarika, See-Kiong Ng, Soujanya Poria, Roger Zimmermann
Scarcity of annotated causal texts leads to poor robustness when training state-of-the-art language models for causal sentence classification.
1 code implementation • RANLP 2021 • Arthur Deschamps, Sujatha Das Gollapalli, See-Kiong Ng
We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG), for learning to generate fact-infused questions from a given question.
no code implementations • 30 May 2024 • Thong Thanh Nguyen, Zhiyuan Hu, Xiaobao Wu, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu
Seeking answers effectively for long videos is essential to build video question answering (videoQA) systems.
1 code implementation • 27 May 2024 • Xiaoqiang Lin, Zhongxiang Dai, Arun Verma, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low
We apply our APOHF algorithm to various tasks, including optimizing user instructions, prompt optimization for text-to-image generative models, and response optimization with human feedback (i. e., further refining the response using a variant of our APOHF).
1 code implementation • 25 May 2024 • Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low
On the other hand, the impact of the instruction, another essential component in the prompt given to the LLM, is often overlooked in existing exemplar selection methods.
no code implementations • 12 May 2024 • Wenjie Wang, Honghui Bao, Xinyu Lin, Jizhi Zhang, Yongqi Li, Fuli Feng, See-Kiong Ng, Tat-Seng Chua
To address these shortcomings, we propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), designed to meet the key criteria of identifiers by integrating hierarchical semantics, collaborative signals, and code assignment diversity.
no code implementations • 18 Apr 2024 • Naibo Wang, Yuchen Deng, Wenjie Feng, Shichen Fan, Jianwei Yin, See-Kiong Ng
In this paper, we improve the one-shot sequential federated learning for non-IID data by proposing a local model diversity-enhancing strategy.
3 code implementations • 11 Apr 2024 • Gregory Kang Ruey Lau, Apivich Hemachandra, See-Kiong Ng, Bryan Kian Hsiang Low
Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints, train with a composite loss function that contains multiple training point types: different types of collocation points chosen during training to enforce each PDE and initial/boundary conditions, and experimental points which are usually costly to obtain via experiments or simulations.
1 code implementation • 27 Mar 2024 • Brian Formento, Wenjie Feng, Chuan Sheng Foo, Luu Anh Tuan, See-Kiong Ng
Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern.
no code implementations • 7 Mar 2024 • Lin Xu, Ningxin Peng, Daquan Zhou, See-Kiong Ng, Jinlan Fu
Dialogue state tracking (DST) aims to record user queries and goals during a conversational interaction achieved by maintaining a predefined set of slots and their corresponding values.
no code implementations • 5 Mar 2024 • Wenyang Hu, Yao Shu, Zongmin Yu, Zhaoxuan Wu, Xiangqiang Lin, Zhongxiang Dai, See-Kiong Ng, Bryan Kian Hsiang Low
Existing methodologies usually prioritize a global optimization for finding the global optimum, which however will perform poorly in certain tasks.
no code implementations • 4 Mar 2024 • Lin Xu, Qixian Zhou, Jinlan Fu, See-Kiong Ng
Knowledge-grounded dialogue systems aim to generate coherent and engaging responses based on the dialogue contexts and selected external knowledge.
no code implementations • 4 Mar 2024 • Fiona Anting Tan, Gerard Christopher Yeo, Fanyou Wu, Weijie Xu, Vinija Jain, Aman Chadha, Kokil Jaidka, Yang Liu, See-Kiong Ng
Drawing inspiration from psychological research on the links between certain personality traits and Theory-of-Mind (ToM) reasoning, and from prompt engineering research on the hyper-sensitivity of prompts in affecting LLMs capabilities, this study investigates how inducing personalities in LLMs using prompts affects their ToM reasoning capabilities.
no code implementations • 23 Feb 2024 • Yang Deng, Yong Zhao, Moxin Li, See-Kiong Ng, Tat-Seng Chua
Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have a definitive answer.
1 code implementation • 23 Feb 2024 • Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, Tat-Seng Chua
Web agents powered by Large Language Models (LLMs) have demonstrated remarkable abilities in planning and executing multi-step interactions within complex web-based environments, fulfilling a wide range of web navigation tasks.
1 code implementation • 22 Feb 2024 • Jinlan Fu, Shenzhen Huangfu, Hang Yan, See-Kiong Ng, Xipeng Qiu
Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains.
no code implementations • 20 Feb 2024 • Jinyu Cai, Yunhe Zhang, Zhoumin Lu, Wenzhong Guo, See-Kiong Ng
Although federated learning offers a promising solution, the prevalent non-IID problems and high communication costs present significant challenges, particularly pronounced in collaborations with graph data distributed among different participants.
no code implementations • 15 Feb 2024 • Jujia Zhao, Wenjie Wang, Chen Xu, Zhaochun Ren, See-Kiong Ng, Tat-Seng Chua
Nevertheless, applying Fed4Rec to LLM-based recommendation presents two main challenges: first, an increase in the imbalance of performance across clients, affecting the system's efficiency over time, and second, a high demand on clients' computational and storage resources for local training and inference of LLMs.
1 code implementation • 12 Feb 2024 • Mingzhe Du, Anh Tuan Luu, Bin Ji, Qian Liu, See-Kiong Ng
Based on the distribution, we introduce a new metric Beyond, which computes a runtime-percentile-weighted Pass score to reflect functional correctness and computational efficiency simultaneously.
no code implementations • 12 Feb 2024 • Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu
Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective.
1 code implementation • 5 Feb 2024 • Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi
In the face of uncertainty, the ability to *seek information* is of fundamental importance.
no code implementations • 28 Dec 2023 • Mingtao Yang, See-Kiong Ng, Jinlan Fu
Furthermore, to glean a nuanced understanding of OmniDialog's strengths and potential pitfalls, we designed a fine-grained analysis framework for dialogue-centric tasks.
1 code implementation • 12 Dec 2023 • Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi Le, Zhiyuan Hu, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization.
no code implementations • 5 Dec 2023 • Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query.
1 code implementation • 1 Nov 2023 • Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, Tat-Seng Chua
Proactive dialogues serve as a practical yet challenging dialogue problem in the era of large language models (LLMs), where the dialogue policy planning is the key to improving the proactivity of LLMs.
1 code implementation • 22 Oct 2023 • Mingzhe Du, Anh Tuan Luu, Bin Ji, See-Kiong Ng
The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks.
1 code implementation • 14 Oct 2023 • Yi Bin, Wenhao Shi, Yujuan Ding, Yang Yang, See-Kiong Ng
Math word problem (MWP) solving aims to understand the descriptive math problem and calculate the result, for which previous efforts are mostly devoted to upgrade different technical modules.
no code implementations • 10 Oct 2023 • Xinyu Lin, Wenjie Wang, Yongqi Li, Fuli Feng, See-Kiong Ng, Tat-Seng Chua
To combat these issues, we propose a novel multi-facet paradigm, namely TransRec, to bridge the LLMs to recommendation.
1 code implementation • 2 Oct 2023 • Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low
We perform instruction optimization for ChatGPT and use extensive experiments to show that our INSTINCT consistently outperforms the existing methods in different tasks, such as in various instruction induction tasks and the task of improving the zero-shot chain-of-thought instruction.
no code implementations • 1 Oct 2023 • Jingtan Wang, Xinyang Lu, Zitong Zhao, Zhongxiang Dai, Chuan-Sheng Foo, See-Kiong Ng, Bryan Kian Hsiang Low
The impressive performances of large language models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the intellectual property (IP) of their training data.
no code implementations • 16 Sep 2023 • Zhiyuan Hu, Yue Feng, Yang Deng, Zekun Li, See-Kiong Ng, Anh Tuan Luu, Bryan Hooi
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practical scenarios.
no code implementations • 7 Jul 2023 • Wenmiao Hu, Yichen Zhang, Yuxuan Liang, Yifang Yin, Andrei Georgescu, An Tran, Hannes Kruppa, See-Kiong Ng, Roger Zimmermann
Street-view imagery provides us with novel experiences to explore different places remotely.
Ranked #3 on Image-Based Localization on cvact
1 code implementation • 9 Jun 2023 • Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Chuan-Sheng Foo, Bryan Kian Hsiang Low
In collaborative learning with streaming data, nodes (e. g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data.
1 code implementation • 7 Jun 2023 • Apivich Hemachandra, Zhongxiang Dai, Jasraj Singh, See-Kiong Ng, Bryan Kian Hsiang Low
To this end, we introduce our expected variance with Gaussian processes (EV-GP) criterion for neural active learning, which is theoretically guaranteed to select data points which lead to trained NNs with both (a) good predictive performances and (b) initialization robustness.
no code implementations • 22 May 2023 • Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Viktor Schlegel, Stefan Winkler, See-Kiong Ng, Soujanya Poria
In this paper, we provide an overview of the different methods for sentence representation learning, focusing mostly on deep learning models.
no code implementations • 16 May 2023 • Fiona Anting Tan, Debdeep Paul, Sahim Yamaura, Miura Koji, See-Kiong Ng
In this work, we propose a methodology to construct causal knowledge graphs (KGs) from news using two steps: (1) Extraction of Causal Relations, and (2) Argument Clustering and Representation into KG.
1 code implementation • 8 May 2023 • Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, See-Kiong Ng, Heng Tao Shen
For evaluating the possible expression variants, we design a path-based metric to evaluate the partial accuracy of expressions of a unified tree.
1 code implementation • ACM The Web Conference 2023 • Naibo Wang, Wenjie Feng, Jianwei Yin, See-Kiong Ng
As such, web-crawling is an essential tool for both computational and non-computational scientists to conduct research.
1 code implementation • 23 Feb 2023 • Naibo Wang, Wenjie Feng, Fusheng Liu, Moming Duan, See-Kiong Ng
The emerging availability of trained machine learning models has put forward the novel concept of Machine Learning Model Market in which one can harness the collective intelligence of multiple well-trained models to improve the performance of the resultant model through one-shot federated learning and ensemble learning in a data-free manner.
2 code implementations • 8 Feb 2023 • Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, PengFei Liu
Generative Artificial Intelligence (AI) has enabled the development of sophisticated models that are capable of producing high-caliber text, images, and other outputs through the utilization of large pre-trained models.
no code implementations • 31 Jan 2023 • Kiran Krishnamachari, See-Kiong Ng, Chuan-Sheng Foo
Using this result, we propose a general measure of any differentiable model's Fourier-sensitivity using the unitary Fourier-transform of its input-gradient.
no code implementations • COLING 2022 • Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, See-Kiong Ng
Knowledge-grounded dialog systems need to incorporate smooth transitions among knowledge selected for generating responses, to ensure that dialog flows naturally.
no code implementations • 25 Sep 2022 • Nicholas Lim, Bryan Hooi, See-Kiong Ng, Yong Liang Goh
Sparsity of the User-POI matrix is a well established problem for next POI recommendation, which hinders effective learning of user preferences.
1 code implementation • 19 Aug 2022 • Fiona Anting Tan, Xinyu Zuo, See-Kiong Ng
Current causal text mining datasets vary in objectives, data coverage, and annotation schemes.
1 code implementation • 5 Jul 2022 • Thong Nguyen, Cong-Duy Nguyen, Xiaobao Wu, See-Kiong Ng, Anh Tuan Luu
Moreover, a list of training datasets and downstream tasks is supplied to further polish the perspective into V\&L pretraining.
no code implementations • NAACL 2022 • Yang Xiao, Jinlan Fu, See-Kiong Ng, PengFei Liu
In this paper, we ask the research question of whether all the datasets in the benchmark are necessary.
1 code implementation • 29 Apr 2022 • Jinlan Fu, See-Kiong Ng, PengFei Liu
This paper aims for a potential architectural improvement for multilingual learning and asks: Can different tasks from different languages be modeled in a monolithic framework, i. e. without any task/language-specific module?
no code implementations • 1 Apr 2022 • Fangyi Zhu, See-Kiong Ng, Stéphane Bressan
We present an outlook attention mechanism, COOL, for natural language processing.
no code implementations • 1 Apr 2022 • Fangyi Zhu, Lok You Tan, See-Kiong Ng, Stéphane Bressan
Large neural language models are steadily contributing state-of-the-art performance to question answering and other natural language and information processing tasks.
no code implementations • 13 Jan 2022 • Weiling Chen, Sheng Lun Benjamin Chua, Stefan Winkler, See-Kiong Ng
To tackle the issue, we have organized the Trusted Media Challenge (TMC) to explore how Artificial Intelligence (AI) technologies could be leveraged to combat fake media.
1 code implementation • FNP 2021 • Fiona Anting Tan, See-Kiong Ng
Automatic identification of cause-effect spans in financial documents is important for causality modelling and understanding reasons that lead to financial events.
no code implementations • 29 Sep 2021 • Kiran Chari, Chuan-Sheng Foo, See-Kiong Ng
The ability to generalize to out-of-distribution data is a major challenge for modern deep neural networks.
no code implementations • 19 Jan 2021 • Dacheng Chen, Dan Li, Xiuqin Xu, Ruizhi Yang, See-Kiong Ng
We trained our model using the publicly available dataset from 2017 PhysioNet Computing in Cardiology(CinC) Challenge containing 8528 single-lead ECG recordings of short-term heart rhythms (9-61s).
1 code implementation • 3 Dec 2020 • Nicholas Lim, Bryan Hooi, See-Kiong Ng, Xueou Wang, Yong Liang Goh, Renrong Weng, Rui Tan
Next destination recommendation is an important task in the transportation domain of taxi and ride-hailing services, where users are recommended with personalized destinations given their current origin location.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Sujatha Das Gollapalli, Polina Rozenshtein, See-Kiong Ng
Accurate detection of emotions in user- generated text was shown to have several applications for e-commerce, public well-being, and disaster management.
no code implementations • 6 Oct 2020 • Nicholas Lim, Bryan Hooi, See-Kiong Ng, Xueou Wang, Yong Liang Goh, Renrong Weng, Jagannadan Varadarajan
Next Point-of-Interest (POI) recommendation is a longstanding problem across the domains of Location-Based Social Networks (LBSN) and transportation.
no code implementations • 18 Feb 2019 • Baihong Jin, Dan Li, Seshadhri Srinivasan, See-Kiong Ng, Kameshwar Poolla, Alberto~Sangiovanni-Vincentelli
Early detection of incipient faults is of vital importance to reducing maintenance costs, saving energy, and enhancing occupant comfort in buildings.
1 code implementation • 15 Jan 2019 • Dan Li, Dacheng Chen, Lei Shi, Baihong Jin, Jonathan Goh, See-Kiong Ng
The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems.
2 code implementations • 13 Sep 2018 • Dan Li, Dacheng Chen, Jonathan Goh, See-Kiong Ng
We used LSTM-RNN in our GAN to capture the distribution of the multivariate time series of the sensors and actuators under normal working conditions of a CPS.