no code implementations • CCL 2020 • Wenyu Guan, Qianying Liu, Tianyi Li, Sujian Li
To solve this problem, we propose a two-step approach which first selects and orders the important data records and then generates text from the noise-reduced data.
1 code implementation • ACL (IWPT) 2021 • Tianyi Li, Sujian Li, Mark Steedman
Strong and affordable in-domain data is a desirable asset when transferring trained semantic parsers to novel domains.
no code implementations • 14 Mar 2024 • Jianwei Sun, Chaoyang Mei, Linlin Wei, Kaiyu Zheng, Na Liu, Ming Cui, Tianyi Li
The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains.
no code implementations • 22 Feb 2024 • Wendi Zhou, Tianyi Li, Pavlos Vougiouklis, Mark Steedman, Jeff Z. Pan
Identifying and understanding user intents is a pivotal task for E-Commerce.
no code implementations • 22 Dec 2023 • Tianyi Li, Joshua Klavins, Te Xu, Niaz Mahmud Zafri, Raphael Stern
Our analysis indicates that vehicle speed, the presence of parking lots, proximity to parks or schools, and the width of major road crossings significantly influence driver yielding at unsignalized intersections.
no code implementations • 12 Dec 2023 • Tianyi Li, Alexander Halatsis, Raphael Stern
This paper introduces RACER, the Rational Artificial Intelligence Car-following model Enhanced by Reality, a cutting-edge deep learning car-following model, that satisfies partial derivative constraints, designed to predict Adaptive Cruise Control (ACC) driving behavior while staying theoretically feasible.
no code implementations • 26 Oct 2023 • Tianyi Li, Mingfeng Shang, Shian Wang, Raphael Stern
A novel generative adversarial network (GAN)-based anomaly detection model is proposed for real-time identification of such attacks using vehicle trajectory data.
no code implementations • 5 Jul 2023 • Jiaqi Wang, Tianyi Li, Anni Wang, Xiaoze Liu, Lu Chen, Jie Chen, Jianye Liu, Junyang Wu, Feifei Li, Yunjun Gao
This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis.
1 code implementation • 23 May 2023 • Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson, Mark Steedman
Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization.
1 code implementation • 15 May 2023 • Wentao Ye, Mingfeng Ou, Tianyi Li, Yipeng chen, Xuetao Ma, Yifan Yanggong, Sai Wu, Jie Fu, Gang Chen, Haobo Wang, Junbo Zhao
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
1 code implementation • 14 Apr 2023 • Junyang Wu, Tianyi Li, Lu Chen, Yunjun Gao, Ziheng Wei
To enhance the usability of GNN-based EA models in real-world applications, we present SEA, a scalable entity alignment system that enables to (i) train large-scale GNNs for EA, (ii) speed up the normalization and the evaluation process, and (iii) report clear results for users to estimate different models and parameter settings.
no code implementations • 10 Mar 2023 • Yumeng Song, Yu Gu, Tianyi Li, Jianzhong Qi, Zhenghao Liu, Christian S. Jensen, Ge Yu
However, recent studies on hypergraph learning that extend graph convolutional networks to hypergraphs cannot learn effectively from features of unlabeled data.
1 code implementation • 1 Feb 2023 • Xiaoze Liu, Junyang Wu, Tianyi Li, Lu Chen, Yunjun Gao
State-of-the-art time-aware EA studies have suggested that the temporal information of TKGs facilitates the performance of EA.
Ranked #1 on Entity Alignment on YAGO-WIKI50K
no code implementations • 18 Jan 2023 • Tianyi Li, Michele Buzzicotti, Luca Biferale, Fabio Bonaccorso
We perform a systematic quantitative benchmark of point-wise and statistical reconstruction capabilities of the linear Extended Proper Orthogonal Decomposition (EPOD) method, a non-linear Convolutional Neural Network (CNN) and a Generative Adversarial Network (GAN).
no code implementations • 11 Dec 2022 • Danlei Hu, Ziquan Fang, Hanxi Fang, Tianyi Li, Chunhui Shen, Lu Chen, Yunjun Gao
Transportation mode classification, the process of predicting the class labels of moving objects transportation modes, has been widely applied to a variety of real world applications, such as traffic management, urban computing, and behavior study.
no code implementations • 21 Oct 2022 • Tianyi Li, Michele Buzzicotti, Luca Biferale, Fabio Bonaccorso, Shiyi Chen, Minping Wan
Different gap sizes and gap geometries are investigated in order to assess the importance of coherency and multi-scale properties of the missing information.
1 code implementation • 10 Oct 2022 • Tianyi Li, Mohammad Javad Hosseini, Sabine Weber, Mark Steedman
We examine LMs' competence of directional predicate entailments by supervised fine-tuning with prompts.
1 code implementation • 26 Aug 2022 • Tianyi Li, WenYu Huang, Nikos Papasarantopoulos, Pavlos Vougiouklis, Jeff Z. Pan
Our system is the winner of track 1 of the LM-KBC challenge, based on BERT LM; it achieves 55. 0% F-1 score on the hidden test set of the challenge.
1 code implementation • 30 Jul 2022 • Nick McKenna, Tianyi Li, Mark Johnson, Mark Steedman
The diversity and Zipfian frequency distribution of natural language predicates in corpora leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE).
no code implementations • 12 Jul 2022 • Tianyi Li
The graph-theoretical task of determining most likely inter-community edges based on disconnected subgraphs' intra-community connectivity is proposed.
2 code implementations • 20 May 2022 • Yunjun Gao, Xiaoze Liu, Junyang Wu, Tianyi Li, Pengfei Wang, Lu Chen
To tackle this challenge, we present ClusterEA, a general framework that is capable of scaling up EA models and enhancing their results by leveraging normalization methods on mini-batches with a high entity equivalent rate.
Ranked #2 on Entity Alignment on DBP1M DE-EN
no code implementations • 26 Apr 2022 • Wenlong Zhang, Bhagyashree Ingale, Hamza Shabir, Tianyi Li, Tian Shi, Ping Wang
ED Explorer consists of an interactive web application, an API, and an NLP toolkit, which can help both domain experts and non-experts to better understand the ED task.
1 code implementation • Findings (ACL) 2022 • Tianyi Li, Sabine Weber, Mohammad Javad Hosseini, Liane Guillou, Mark Steedman
Predicate entailment detection is a crucial task for question-answering from text, where previous work has explored unsupervised learning of entailment graphs from typed open relation triples.
1 code implementation • ECCV 2020 • Qunliang Xing, Mai Xu, Tianyi Li, Zhenyu Guan
Recently, extensive approaches have been proposed to reduce image compression artifacts at the decoder side; however, they require a series of architecture-identical models to process images with different quality, which are inefficient and resource-consuming.
1 code implementation • 23 Jun 2020 • Tianyi Li, Mai Xu, Runzhi Tang, Ying Chen, Qunliang Xing
In VVC, the quad-tree plus multi-type tree (QTMT) structure of coding unit (CU) partition accounts for over 97% of the encoding time, due to the brute-force search for recursive rate-distortion (RD) optimization.
no code implementations • 30 May 2020 • Yunkai Xiao, Gabriel Zingle, Qinjin Jia, Harsh R. Shah, Yi Zhang, Tianyi Li, Mohsin Karovaliya, Weixiang Zhao, Yang song, Jie Ji, Ashwin Balasubramaniam, Harshit Patel, Priyankha Bhalasubbramanian, Vikram Patel, Edward F. Gehringer
We attempt to automate the process of deciding whether a review comment detects a problem.
no code implementations • WS 2019 • Tianyi Li, Sujian Li
Previous work on visual storytelling mainly focused on exploring image sequence as evidence for storytelling and neglected textual evidence for guiding story generation.
no code implementations • 1 Nov 2019 • Pengfei Zhou, Tianyi Li, Pan Zhang
For the first time, well-controlled benchmark datasets with asymptotially exact properties and optimal solutions could be produced for the evaluation of graph convolution neural networks, and for the theoretical understanding of their strengths and weaknesses.
no code implementations • 29 Jun 2019 • Liuyuan Deng, Ming Yang, Tianyi Li, Yuesheng He, Chunxiang Wang
To instantiate this structure, the paper proposes a residual fusion block (RFB) to formulate the interdependences of the encoders.
Ranked #3 on Semantic Segmentation on ScanNetV2
no code implementations • 5 Mar 2019 • Tianyi Li, Mai Xu, Ren Yang, Xiaoming Tao
High efficiency video coding (HEVC) has brought outperforming efficiency for video compression.
1 code implementation • CVPR 2018 • Ren Yang, Mai Xu, Zulin Wang, Tianyi Li
In this paper, we investigate that heavy quality fluctuation exists across compressed video frames, and thus low quality frames can be enhanced using the neighboring high quality frames, seen as Multi-Frame Quality Enhancement (MFQE).
Ranked #6 on Video Enhancement on MFQE v2
no code implementations • 2 Jan 2018 • Liuyuan Deng, Ming Yang, Hao Li, Tianyi Li, Bing Hu, Chunxiang Wang
Finally, an RDC based semantic segmentation model is built; the model is trained for real-world surround view images through a multi-task learning architecture by combining real-world images with transformed images.
1 code implementation • 19 Sep 2017 • Mai Xu, Tianyi Li, Zulin Wang, Xin Deng, Ren Yang, Zhenyu Guan
Therefore, this paper proposes a deep learning approach to predict the CU partition for reducing the HEVC complexity at both intra- and inter-modes, which is based on convolutional neural network (CNN) and long- and short-term memory (LSTM) network.