Search Results for author: Jinfeng Li

Found 19 papers, 7 papers with code

Distilling Salient Reviews with Zero Labels

no code implementations FEVER (ACL) 2022 Chieh-Yang Huang, Jinfeng Li, Nikita Bhutani, Alexander Whedon, Estevam Hruschka, Yoshi Suhara

To alleviate this scarcity problem, we develop an unsupervised method, ZL-Distiller, which leverages contextual language representations of the reviews and their distributional patterns to identify salient sentences about entities.

Question Answering

Annotating Columns with Pre-trained Language Models

1 code implementation5 Apr 2021 Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information.

Multi-Task Learning Table annotation +1

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

no code implementations CVPR 2021 Xiaodan Li, Jinfeng Li, Yuefeng Chen, Shaokai Ye, Yuan He, Shuhui Wang, Hang Su, Hui Xue

Comprehensive experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting.

Image Classification Image Retrieval

Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation

no code implementations23 Feb 2021 Jinfeng Li, Tianyu Du, Xiangyu Liu, Rong Zhang, Hui Xue, Shouling Ji

Extensive experiments on two real-world tasks show that AdvGraph exhibits better performance compared with previous work: (i) effective - it significantly strengthens the model robustness even under the adaptive attacks setting without negative impact on model performance over legitimate input; (ii) generic - its key component, i. e., the representation of connotative adversarial knowledge is task-agnostic, which can be reused in any Chinese-based NLP models without retraining; and (iii) efficient - it is a light-weight defense with sub-linear computational complexity, which can guarantee the efficiency required in practical scenarios.

Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples

no code implementations21 Aug 2020 Jinfeng Li, Weifeng Liu, Yicong Zhou, Jun Yu, Dapeng Tao

Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain.

Domain Adaptation Graph Learning

Deep or Simple Models for Semantic Tagging? It Depends on your Data [Experiments]

no code implementations11 Jul 2020 Jinfeng Li, Yuliang Li, Xiaolan Wang, Wang-Chiew Tan

We embark on a systematic study to investigate the following question: Are deep models the best performing model for all semantic tagging tasks?

TAG

Enhancing Review Comprehension with Domain-Specific Commonsense

no code implementations6 Apr 2020 Aaron Traylor, Chen Chen, Behzad Golshan, Xiaolan Wang, Yuliang Li, Yoshihiko Suhara, Jinfeng Li, Cagatay Demiralp, Wang-Chiew Tan

In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs).

Aspect Extraction Knowledge Distillation +2

Deep Entity Matching with Pre-Trained Language Models

1 code implementation1 Apr 2020 Yuliang Li, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, Wang-Chiew Tan

Our experiments show that a straightforward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets.

Data Augmentation Entity Resolution

A Novel Twitter Sentiment Analysis Model with Baseline Correlation for Financial Market Prediction with Improved Efficiency

no code implementations18 Mar 2020 Xinyi Guo, Jinfeng Li

A novel social networks sentiment analysis model is proposed based on Twitter sentiment score (TSS) for real-time prediction of the future stock market price FTSE 100, as compared with conventional econometric models of investor sentiment based on closed-end fund discount (CEFD).

Decision Making Twitter Sentiment Analysis

Sato: Contextual Semantic Type Detection in Tables

1 code implementation14 Nov 2019 Dan Zhang, Yoshihiko Suhara, Jinfeng Li, Madelon Hulsebos, Çağatay Demiralp, Wang-Chiew Tan

Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search.

Information Retrieval Structured Prediction

Subjective Databases

no code implementations25 Feb 2019 Yuliang Li, Aaron Xixuan Feng, Jinfeng Li, Saran Mumick, Alon Halevy, Vivian Li, Wang-Chiew Tan

In order to support experiential queries, a database system needs to model subjective data and also be able to process queries where the user can express varied subjective experiences in words chosen by the user, in addition to specifying predicates involving objective attributes.

Databases

SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systems

no code implementations23 Jan 2019 Tianyu Du, Shouling Ji, Jinfeng Li, Qinchen Gu, Ting Wang, Raheem Beyah

Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave.

Cryptography and Security

TextBugger: Generating Adversarial Text Against Real-world Applications

1 code implementation13 Dec 2018 Jinfeng Li, Shouling Ji, Tianyu Du, Bo Li, Ting Wang

Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification.

Adversarial Text Machine Translation +5

Norm-Ranging LSH for Maximum Inner Product Search

1 code implementation NeurIPS 2018 Xiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, James Cheng

Neyshabur and Srebro proposed Simple-LSH, which is the state-of-the-art hashing method for maximum inner product search (MIPS) with performance guarantee.

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