Search Results for author: Tianyi Li

Found 33 papers, 14 papers with code

Refining Data for Text Generation

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.

Data-to-Text Generation Learning-To-Rank

Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer

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.

Text-To-SQL

Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse

no code implementations14 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.

A Usage-centric Take on Intent Understanding in E-Commerce

no code implementations22 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.

Understanding driver-pedestrian interactions to predict driver yielding: naturalistic open-source dataset collected in Minnesota

no code implementations22 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.

RACER: Rational Artificial Intelligence Car-following-model Enhanced by Reality

no code implementations12 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.

Detecting stealthy cyberattacks on adaptive cruise control vehicles: A machine learning approach

no code implementations26 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.

Anomaly Detection Generative Adversarial Network

Real-time Workload Pattern Analysis for Large-scale Cloud Databases

no code implementations5 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.

Sources of Hallucination by Large Language Models on Inference Tasks

1 code implementation23 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.

Hallucination Memorization +2

Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility

1 code implementation15 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.

Memorization

SEA: A Scalable Entity Alignment System

1 code implementation14 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.

Entity Alignment Knowledge Graphs

CHGNN: A Semi-Supervised Contrastive Hypergraph Learning Network

no code implementations10 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.

Contrastive Learning Node Classification

Unsupervised Entity Alignment for Temporal Knowledge Graphs

1 code implementation1 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.

Entity Alignment Graph Matching +1

Generative Adversarial Networks to infer velocity components in rotating turbulent flows

no code implementations18 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).

Generative Adversarial Network

Estimator: An Effective and Scalable Framework for Transportation Mode Classification over Trajectories

no code implementations11 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.

Classification Management

Language Models Are Poor Learners of Directional Inference

1 code implementation10 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.

Task-specific Pre-training and Prompt Decomposition for Knowledge Graph Population with Language Models

1 code implementation26 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.

Retrieval

Smoothing Entailment Graphs with Language Models

1 code implementation30 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).

Explainable Models Language Modelling +2

Edge Augmentation on Disconnected Graphs via Eigenvalue Elevation

no code implementations12 Jul 2022 Tianyi Li

The graph-theoretical task of determining most likely inter-community edges based on disconnected subgraphs' intra-community connectivity is proposed.

Community Detection

ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities

2 code implementations20 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.

Entity Alignment Entity Embeddings +1

Event Detection Explorer: An Interactive Tool for Event Detection Exploration

no code implementations26 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.

Event Detection

Cross-lingual Inference with A Chinese Entailment Graph

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.

Entity Typing Question Answering +2

Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images

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.

Image Enhancement Image Restoration

DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC

1 code implementation23 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.

Incorporating Textual Evidence in Visual Storytelling

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.

Object Recognition Visual Storytelling

Phase transitions and optimal algorithms for semi-supervised classifications on graphs: from belief propagation to graph convolution network

no code implementations1 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.

Bayesian Inference Clustering +2

RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation

no code implementations29 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.

Semantic Segmentation

Multi-Frame Quality Enhancement for Compressed Video

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).

Motion Compensation Video Enhancement

Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras

no code implementations2 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.

Autonomous Driving Multi-Task Learning +2

Reducing Complexity of HEVC: A Deep Learning Approach

1 code implementation19 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.