Search Results for author: Wei Lu

Found 143 papers, 72 papers with code

Re-examining the Role of Schema Linking in Text-to-SQL

no code implementations EMNLP 2020 Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua

By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study the role of schema linking.

Text-To-SQL

SmartCiteCon: Implicit Citation Context Extraction from Academic Literature Using Supervised Learning

no code implementations WOSP 2020 Chenrui Guo, Haoran Cui, Li Zhang, Jiamin Wang, Wei Lu, Jian Wu

The tool is built on a Support Vector Machine (SVM) model trained on a set of 7, 058 manually annotated citation context sentences, curated from 34, 000 papers from the ACL Anthology.

Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation

no code implementations23 Feb 2024 Aditya Desu, Xuanli He, Qiongkai Xu, Wei Lu

As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of generated data.

Misinformation

Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning

1 code implementation16 Feb 2024 Yinpeng Liu, Jiawei Liu, Xiang Shi, Qikai Cheng, Wei Lu

We advocate the few-shot in-context curriculum learning (ICCL), a simple but effective demonstration ordering method for ICL, which implies gradually increasing the complexity of prompt demonstrations during the inference process.

In-Context Learning

Anomaly Detection of Particle Orbit in Accelerator using LSTM Deep Learning Technology

no code implementations28 Jan 2024 ZhiYuan Chen, Wei Lu, Radhika Bhong, Yimin Hu, Brian Freeman, Adam Carpenter

A stable, reliable, and controllable orbit lock system is crucial to an electron (or ion) accelerator because the beam orbit and beam energy instability strongly affect the quality of the beam delivered to experimental halls.

Anomaly Detection Fault Detection

TinyLlama: An Open-Source Small Language Model

3 code implementations4 Jan 2024 Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, Wei Lu

We present TinyLlama, a compact 1. 1B language model pretrained on around 1 trillion tokens for approximately 3 epochs.

Computational Efficiency Language Modelling

Disentangling the Potential Impacts of Papers into Diffusion, Conformity, and Contribution Values

no code implementations15 Nov 2023 Zhikai Xue, Guoxiu He, Zhuoren Jiang, Sichen Gu, Yangyang Kang, Star Zhao, Wei Lu

In this study, we propose a novel graph neural network to Disentangle the Potential impacts of Papers into Diffusion, Conformity, and Contribution values (called DPPDCC).

Unraveling Feature Extraction Mechanisms in Neural Networks

1 code implementation25 Oct 2023 Xiaobing Sun, Jiaxi Li, Wei Lu

The underlying mechanism of neural networks in capturing precise knowledge has been the subject of consistent research efforts.

Language Modelling

Tuna: Instruction Tuning using Feedback from Large Language Models

1 code implementation20 Oct 2023 Haoran Li, Yiran Liu, Xingxing Zhang, Wei Lu, Furu Wei

Furthermore, we apply probabilistic ranking and contextual ranking sequentially to the instruction-tuned LLM.

Know Where to Go: Make LLM a Relevant, Responsible, and Trustworthy Searcher

no code implementations19 Oct 2023 Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng, Wei Lu

The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches.

Hallucination Information Retrieval +1

Decomposed Prompt Tuning via Low-Rank Reparameterization

1 code implementation16 Oct 2023 Yao Xiao, Lu Xu, Jiaxi Li, Wei Lu, XiaoLi Li

While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft prompt is either randomly initialized or derived from an existing embedding vocabulary.

Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning

1 code implementation20 Sep 2023 Wenhang Shi, Yiren Chen, Zhe Zhao, Wei Lu, Kimmo Yan, Xiaoyong Du

Therefore, we shift the attention to the current task learning stage, presenting a novel framework, C&F (Create and Find Flatness), which builds a flat training space for each task in advance.

Continual Learning

Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers

1 code implementation1 Jun 2023 Jiaxi Li, Wei Lu

To leverage this knowledge, we propose a novel chart-based method for extracting parse trees from masked language models (LMs) without the need to train separate parsers.

Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning

1 code implementation29 May 2023 Zhanming Jie, Wei Lu

To address these issues, we investigate two approaches to leverage the training data in a few-shot prompting scenario: dynamic program prompting and program distillation.

Language Modelling Large Language Model +1

Tab-CoT: Zero-shot Tabular Chain of Thought

2 code implementations28 May 2023 Ziqi Jin, Wei Lu

The chain-of-though (CoT) prompting methods were successful in various natural language processing (NLP) tasks thanks to their ability to unveil the underlying complex reasoning processes.

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning

1 code implementation28 May 2023 Guangtao Zeng, Peiyuan Zhang, Wei Lu

Fine-tuning pre-trained language models for multiple tasks tends to be expensive in terms of storage.

Transfer Learning

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

1 code implementation22 May 2023 Lu Xu, Lidong Bing, Wei Lu

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations.

named-entity-recognition Named Entity Recognition +1

CIT-EmotionNet: CNN Interactive Transformer Network for EEG Emotion Recognition

no code implementations7 May 2023 Wei Lu, Hua Ma, Tien-Ping Tan

Emotion recognition using Electroencephalogram (EEG) signals has emerged as a significant research challenge in affective computing and intelligent interaction.

EEG EEG Emotion Recognition +1

Low-Resource Multi-Granularity Academic Function Recognition Based on Multiple Prompt Knowledge

no code implementations5 May 2023 Jiawei Liu, Zi Xiong, Yi Jiang, Yongqiang Ma, Wei Lu, Yong Huang, Qikai Cheng

Inspired by recent advancement in prompt learning, in this paper, we propose the Mix Prompt Tuning (MPT), which is a semi-supervised method to alleviate the dependence on annotated data and improve the performance of multi-granularity academic function recognition tasks with a small number of labeled examples.

Sentence

H2CGL: Modeling Dynamics of Citation Network for Impact Prediction

1 code implementation16 Apr 2023 Guoxiu He, Zhikai Xue, Zhuoren Jiang, Yangyang Kang, Star Zhao, Wei Lu

Then, a novel graph neural network, Hierarchical and Heterogeneous Contrastive Graph Learning Model (H2CGL), is proposed to incorporate heterogeneity and dynamics of the citation network.

Contrastive Learning Graph Learning

Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturing

no code implementations11 Apr 2023 Wei Lu, Nic A. Lee, Markus J. Buehler

Spider webs are incredible biological structures, comprising thin but strong silk filament and arranged into complex hierarchical architectures with striking mechanical properties (e. g., lightweight but high strength, achieving diverse mechanical responses).

graph construction

Online stochastic Newton methods for estimating the geometric median and applications

no code implementations3 Apr 2023 Antoine Godichon-Baggioni, Wei Lu

In the context of large samples, a small number of individuals might spoil basic statistical indicators like the mean.

MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos

1 code implementation CVPR 2023 ZiCheng Zhang, Wei Wu, Wei Sun, Dangyang Tu, Wei Lu, Xiongkuo Min, Ying Chen, Guangtao Zhai

User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities.

Video Quality Assessment Visual Question Answering (VQA)

A General-Purpose Transferable Predictor for Neural Architecture Search

no code implementations21 Feb 2023 Fred X. Han, Keith G. Mills, Fabian Chudak, Parsa Riahi, Mohammad Salameh, Jialin Zhang, Wei Lu, Shangling Jui, Di Niu

In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators.

Contrastive Learning Graph Representation Learning +1

EEP-3DQA: Efficient and Effective Projection-based 3D Model Quality Assessment

no code implementations17 Feb 2023 ZiCheng Zhang, Wei Sun, Yingjie Zhou, Wei Lu, Yucheng Zhu, Xiongkuo Min, Guangtao Zhai

Currently, great numbers of efforts have been put into improving the effectiveness of 3D model quality assessment (3DQA) methods.

AI vs. Human -- Differentiation Analysis of Scientific Content Generation

no code implementations24 Jan 2023 Yongqiang Ma, Jiawei Liu, Fan Yi, Qikai Cheng, Yong Huang, Wei Lu, Xiaozhong Liu

We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text.

Text Detection

DDH-QA: A Dynamic Digital Humans Quality Assessment Database

1 code implementation24 Dec 2022 ZiCheng Zhang, Yingjie Zhou, Wei Sun, Wei Lu, Xiongkuo Min, Yu Wang, Guangtao Zhai

In recent years, large amounts of effort have been put into pushing forward the real-world application of dynamic digital human (DDH).

Video Quality Assessment

Named Entity and Relation Extraction with Multi-Modal Retrieval

1 code implementation3 Dec 2022 Xinyu Wang, Jiong Cai, Yong Jiang, Pengjun Xie, Kewei Tu, Wei Lu

MoRe contains a text retrieval module and an image-based retrieval module, which retrieve related knowledge of the input text and image in the knowledge corpus respectively.

Multi-modal Named Entity Recognition Named Entity Recognition +4

GENNAPE: Towards Generalized Neural Architecture Performance Estimators

1 code implementation30 Nov 2022 Keith G. Mills, Fred X. Han, Jialin Zhang, Fabian Chudak, Ali Safari Mamaghani, Mohammad Salameh, Wei Lu, Shangling Jui, Di Niu

In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble.

Contrastive Learning Image Classification +1

Differentiable Data Augmentation for Contrastive Sentence Representation Learning

1 code implementation29 Oct 2022 Tianduo Wang, Wei Lu

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations.

Contrastive Learning Data Augmentation +3

Better Few-Shot Relation Extraction with Label Prompt Dropout

1 code implementation25 Oct 2022 Peiyuan Zhang, Wei Lu

Our experiments show that our approach is able to lead to improved class representations, yielding significantly better results on the few-shot relation extraction task.

Few-Shot Learning Relation +1

Unsupervised Non-transferable Text Classification

1 code implementation23 Oct 2022 Guangtao Zeng, Wei Lu

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property.

text-classification Text Classification

Generative Prompt Tuning for Relation Classification

1 code implementation22 Oct 2022 Jiale Han, Shuai Zhao, Bo Cheng, Shengkun Ma, Wei Lu

Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems by adding cloze-style phrases and mapping all labels to verbalizations with fixed length, which has proven effective for tasks with simple label spaces.

Classification Language Modelling +4

Subjective Quality Assessment for Images Generated by Computer Graphics

no code implementations10 Jun 2022 Tao Wang, ZiCheng Zhang, Wei Sun, Xiongkuo Min, Wei Lu, Guangtao Zhai

However, limited work has been put forward to tackle the problem of computer graphics generated images' quality assessment (CG-IQA).

No-Reference Image Quality Assessment NR-IQA

A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences

no code implementations9 Jun 2022 Yu Fan, ZiCheng Zhang, Wei Sun, Xiongkuo Min, Wei Lu, Tao Wang, Ning Liu, Guangtao Zhai

Point cloud is one of the most widely used digital formats of 3D models, the visual quality of which is quite sensitive to distortions such as downsampling, noise, and compression.

Point Cloud Quality Assessment

Deep Neural Network for Blind Visual Quality Assessment of 4K Content

no code implementations9 Jun 2022 Wei Lu, Wei Sun, Xiongkuo Min, Wenhan Zhu, Quan Zhou, Jun He, Qiyuan Wang, ZiCheng Zhang, Tao Wang, Guangtao Zhai

In this paper, we propose a deep learning-based BIQA model for 4K content, which on one hand can recognize true and pseudo 4K content and on the other hand can evaluate their perceptual visual quality.

Blind Image Quality Assessment Multi-Task Learning

Blind Surveillance Image Quality Assessment via Deep Neural Network Combined with the Visual Saliency

no code implementations9 Jun 2022 Wei Lu, Wei Sun, Wenhan Zhu, Xiongkuo Min, ZiCheng Zhang, Tao Wang, Guangtao Zhai

In this paper, we first conduct an example experiment (i. e. the face detection task) to demonstrate that the quality of the SIs has a crucial impact on the performance of the IVSS, and then propose a saliency-based deep neural network for the blind quality assessment of the SIs, which helps IVSS to filter the low-quality SIs and improve the detection and recognition performance.

Face Detection Image Quality Assessment

A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps

no code implementations9 Jun 2022 ZiCheng Zhang, Wei Sun, Xiongkuo Min, Wenhan Zhu, Tao Wang, Wei Lu, Guangtao Zhai

Therefore, in this paper, we propose a no-reference deep-learning image quality assessment method based on frequency maps because the artifacts caused by SISR algorithms are quite sensitive to frequency information.

Image Quality Assessment Image Super-Resolution

Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

no code implementations28 May 2022 Kai Hu, Yu Liu, Renhe Liu, Wei Lu, Gang Yu, Bin Fu

In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy.

Blind Face Restoration Super-Resolution

ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning

no code implementations21 May 2022 Zechen Liang, Yuan-Gen Wang, Wei Lu, Xiaochun Cao

Semi-Supervised Learning (SSL) has advanced classification tasks by inputting both labeled and unlabeled data to train a model jointly.

Implicit N-grams Induced by Recurrence

1 code implementation NAACL 2022 Xiaobing Sun, Wei Lu

Although self-attention based models such as Transformers have achieved remarkable successes on natural language processing (NLP) tasks, recent studies reveal that they have limitations on modeling sequential transformations (Hahn, 2020), which may prompt re-examinations of recurrent neural networks (RNNs) that demonstrated impressive results on handling sequential data.

Language Modelling Negation +1

A Deep Learning based No-reference Quality Assessment Model for UGC Videos

1 code implementation29 Apr 2022 Wei Sun, Xiongkuo Min, Wei Lu, Guangtao Zhai

The proposed model utilizes very sparse frames to extract spatial features and dense frames (i. e. the video chunk) with a very low spatial resolution to extract motion features, which thereby has low computational complexity.

Image Quality Assessment Video Quality Assessment

L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning

no code implementations25 Sep 2021 Keith G. Mills, Fred X. Han, Mohammad Salameh, SEYED SAEED CHANGIZ REZAEI, Linglong Kong, Wei Lu, Shuo Lian, Shangling Jui, Di Niu

In this paper, we propose L$^{2}$NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the distribution of high-performing architectures in the search history.

Hyperparameter Optimization Neural Architecture Search +2

Profiling Neural Blocks and Design Spaces for Mobile Neural Architecture Search

1 code implementation25 Sep 2021 Keith G. Mills, Fred X. Han, Jialin Zhang, SEYED SAEED CHANGIZ REZAEI, Fabian Chudak, Wei Lu, Shuo Lian, Shangling Jui, Di Niu

Neural architecture search automates neural network design and has achieved state-of-the-art results in many deep learning applications.

Neural Architecture Search

A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis

1 code implementation EMNLP 2021 Jiawei Liu, Kaisong Song, Yangyang Kang, Guoxiu He, Zhuoren Jiang, Changlong Sun, Wei Lu, Xiaozhong Liu

Chatbot is increasingly thriving in different domains, however, because of unexpected discourse complexity and training data sparseness, its potential distrust hatches vital apprehension.

Chatbot Multi-Task Learning

Exploring Task Difficulty for Few-Shot Relation Extraction

1 code implementation EMNLP 2021 Jiale Han, Bo Cheng, Wei Lu

Few-shot relation extraction (FSRE) focuses on recognizing novel relations by learning with merely a handful of annotated instances.

Contrastive Learning Meta-Learning +2

Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction

1 code implementation11 Sep 2021 Guoshun Nan, Guoqing Luo, Sicong Leng, Yao Xiao, Wei Lu

Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues.

Dialog Relation Extraction Relation

No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models

2 code implementations5 Jul 2021 ZiCheng Zhang, Wei Sun, Xiongkuo Min, Tao Wang, Wei Lu, Guangtao Zhai

Therefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the visual quality degradations of 3D models.

Point Cloud Quality Assessment

Mixed Cross Entropy Loss for Neural Machine Translation

1 code implementation30 Jun 2021 Haoran Li, Wei Lu

In neural machine translation, cross entropy (CE) is the standard loss function in two training methods of auto-regressive models, i. e., teacher forcing and scheduled sampling.

Machine Translation Translation

Detection of Deepfake Videos Using Long Distance Attention

no code implementations24 Jun 2021 Wei Lu, Lingyi Liu, Junwei Luo, Xianfeng Zhao, Yicong Zhou, Jiwu Huang

And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces in global perspective respectively.

Binary Classification Face Swapping

Interventional Video Grounding with Dual Contrastive Learning

1 code implementation CVPR 2021 Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu

2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.

Causal Inference Contrastive Learning +2

Generative Adversarial Neural Architecture Search

no code implementations19 May 2021 SEYED SAEED CHANGIZ REZAEI, Fred X. Han, Di Niu, Mohammad Salameh, Keith Mills, Shuo Lian, Wei Lu, Shangling Jui

Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess.

Neural Architecture Search

A parallel-network continuous quantitative trading model with GARCH and PPO

no code implementations8 May 2021 Zhishun Wang, Wei Lu, Kaixin Zhang, TianHao Li, Zixi Zhao

It is a difficult task for both professional investors and individual traders continuously making profit in stock market.

Decision Making reinforcement-learning +1

Better Feature Integration for Named Entity Recognition

1 code implementation NAACL 2021 Lu Xu, Zhanming Jie, Wei Lu, Lidong Bing

We believe this is because both types of features - the contextual information captured by the linear sequences and the structured information captured by the dependency trees may complement each other.

named-entity-recognition Named Entity Recognition +1

Counterfactual Thinking for Long-tailed Information Extraction

no code implementations1 Jan 2021 Guoshun Nan, Jiaqi Zeng, Rui Qiao, Wei Lu

However, in practice, the long-tailed and imbalanced data may lead to severe bias issues for deep learning models, due to very few training instances available for the tail classes.

Causal Inference counterfactual +9

SEQUENCE-LEVEL FEATURES: HOW GRU AND LSTM CELLS CAPTURE N-GRAMS

no code implementations1 Jan 2021 Xiaobing Sun, Wei Lu

Based on the closed-form approximations of the hidden states, we argue that the effectiveness of the cells may be attributed to a type of sequence-level representations brought in by the gating mechanism, which enables the cells to encode sequence-level features along with token-level features.

Language Modelling Rolling Shutter Correction +1

Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders

2 code implementations EMNLP 2020 Jue Wang, Wei Lu

In this work, we propose the novel {\em table-sequence encoders} where two different encoders -- a table encoder and a sequence encoder are designed to help each other in the representation learning process.

Joint Entity and Relation Extraction named-entity-recognition +5

Aspect Based Sentiment Analysis with Aspect-Specific Opinion Spans

1 code implementation EMNLP 2020 Lu Xu, Lidong Bing, Wei Lu, Fei Huang

Such a design allows the model to extract aspect-specific opinion spans and then evaluate sentiment polarity by exploiting the extracted opinion features.

Aspect-Based Sentiment Analysis Extract Aspect

Position-Aware Tagging for Aspect Sentiment Triplet Extraction

4 code implementations EMNLP 2020 Lu Xu, Hao Li, Wei Lu, Lidong Bing

Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach.

Aspect Sentiment Triplet Extraction Position

RPT: Learning Point Set Representation for Siamese Visual Tracking

no code implementations8 Aug 2020 Ziang Ma, Linyuan Wang, HaiTao Zhang, Wei Lu, Jun Yin

While remarkable progress has been made in robust visual tracking, accurate target state estimation still remains a highly challenging problem.

Semi-Supervised Video Object Segmentation Visual Tracking

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

2 code implementations ACL 2020 Guoshun Nan, Zhijiang Guo, Ivan Sekulić, Wei Lu

Document-level relation extraction requires integrating information within and across multiple sentences of a document and capturing complex interactions between inter-sentence entities.

Document-level Relation Extraction Relation +2

WN-Salience: A Corpus of News Articles with Entity Salience Annotations

no code implementations LREC 2020 Chuan Wu, Evangelos Kanoulas, Maarten de Rijke, Wei Lu

To support research on entity salience, we present a new dataset, the WikiNews Salience dataset (WN-Salience), which can be used to benchmark tasks such as entity salience detection and salient entity linking.

Entity Linking

ENT-DESC: Entity Description Generation by Exploring Knowledge Graph

1 code implementation EMNLP 2020 Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu, Luo Si

Previous works on knowledge-to-text generation take as input a few RDF triples or key-value pairs conveying the knowledge of some entities to generate a natural language description.

Graph-to-Sequence KG-to-Text Generation +2

Pre-training for Abstractive Document Summarization by Reinstating Source Text

no code implementations EMNLP 2020 Yanyan Zou, Xingxing Zhang, Wei Lu, Furu Wei, Ming Zhou

The main idea is that, given an input text artificially constructed from a document, a model is pre-trained to reinstate the original document.

Abstractive Text Summarization Document Summarization +1

Adversarial Deep Network Embedding for Cross-network Node Classification

2 code implementations18 Feb 2020 Xiao Shen, Quanyu Dai, Fu-Lai Chung, Wei Lu, Kup-Sze Choi

This motivates us to propose an adversarial cross-network deep network embedding (ACDNE) model to integrate adversarial domain adaptation with deep network embedding so as to learn network-invariant node representations that can also well preserve the network structural information.

Classification Domain Adaptation +3

Mining Commonsense Facts from the Physical World

no code implementations8 Feb 2020 Yanyan Zou, Wei Lu, Xu sun

In this paper, we propose a new task of mining commonsense facts from the raw text that describes the physical world.

Knowledge Base Completion

Self-Directed Online Machine Learning for Topology Optimization

1 code implementation4 Feb 2020 Changyu Deng, Yizhou Wang, Can Qin, Yun Fu, Wei Lu

A small number of training data is generated dynamically based on the DNN's prediction of the optimum.

BIG-bench Machine Learning Stochastic Optimization

Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model

no code implementations3 Jan 2020 Guoxiu He, Zhe Gao, Zhuoren Jiang, Yangyang Kang, Changlong Sun, Xiaozhong Liu, Wei Lu

The nonliteral interpretation of a text is hard to be understood by machine models due to its high context-sensitivity and heavy usage of figurative language.

Reading Comprehension Sentence

Learning Explicit and Implicit Structures for Targeted Sentiment Analysis

no code implementations IJCNLP 2019 Hao Li, Wei Lu

In this work, we argue that both types of information (implicit and explicit structural information) are crucial for building a successful targeted sentiment analysis model.

Sentiment Analysis

UER: An Open-Source Toolkit for Pre-training Models

1 code implementation IJCNLP 2019 Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.

Combining Spans into Entities: A Neural Two-Stage Approach for Recognizing Discontiguous Entities

1 code implementation IJCNLP 2019 Bailin Wang, Wei Lu

In medical documents, it is possible that an entity of interest not only contains a discontiguous sequence of words but also overlaps with another entity.

Joint Detection and Location of English Puns

1 code implementation NAACL 2019 Yanyan Zou, Wei Lu

A pun is a form of wordplay for an intended humorous or rhetorical effect, where a word suggests two or more meanings by exploiting polysemy (homographic pun) or phonological similarity to another word (heterographic pun).

Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems

1 code implementation ACL 2019 Yanyan Zou, Wei Lu

An arithmetic word problem typically includes a textual description containing several constant quantities.

Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning

1 code implementation TACL 2019 Zhijiang Guo, Yan Zhang, Zhiyang Teng, Wei Lu

We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation.

Graph-to-Sequence Machine Translation +2

Twitter Homophily: Network Based Prediction of User's Occupation

1 code implementation ACL 2019 Jiaqi Pan, Rishabh Bhardwaj, Wei Lu, Hai Leong Chieu, Xinghao Pan, Ni Yi Puay

In this paper, we investigate the importance of social network information compared to content information in the prediction of a Twitter user{'}s occupational class.

Attention Guided Graph Convolutional Networks for Relation Extraction

2 code implementations ACL 2019 Zhijiang Guo, Yan Zhang, Wei Lu

Dependency trees convey rich structural information that is proven useful for extracting relations among entities in text.

Relation Relation Extraction +1

Neural Chinese Address Parsing

no code implementations NAACL 2019 Hao Li, Wei Lu, Pengjun Xie, Linlin Li

This paper introduces a new task {--} Chinese address parsing {--} the task of mapping Chinese addresses into semantically meaningful chunks.

Structured Prediction

Better Modeling of Incomplete Annotations for Named Entity Recognition

no code implementations NAACL 2019 Zhanming Jie, Pengjun Xie, Wei Lu, Ruixue Ding, Linlin Li

Supervised approaches to named entity recognition (NER) are largely developed based on the assumption that the training data is fully annotated with named entity information.

named-entity-recognition Named Entity Recognition +1

Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators

1 code implementation EMNLP 2017 Aldrian Obaja Muis, Wei Lu

We present some theoretical analysis on the differences between our model and a recently proposed model for recognizing overlapping mentions, and discuss the possible implications of the differences.

Efficient Dependency-Guided Named Entity Recognition

1 code implementation19 Oct 2018 Zhanming Jie, Aldrian Obaja Muis, Wei Lu

It has been shown previously that such information can be used to improve the performance of NER (Sasano and Kurohashi 2008, Ling and Weld 2012).

named-entity-recognition Named Entity Recognition +2

Weak Semi-Markov CRFs for NP Chunking in Informal Text

no code implementations19 Oct 2018 Aldrian Obaja Muis, Wei Lu

This paper introduces a new annotated corpus based on an existing informal text corpus: the NUS SMS Corpus (Chen and Kan, 2013).

Chunking

Learning to Recognize Discontiguous Entities

1 code implementation EMNLP 2016 Aldrian Obaja Muis, Wei Lu

This paper focuses on the study of recognizing discontiguous entities.

Neural Adaptation Layers for Cross-domain Named Entity Recognition

1 code implementation EMNLP 2018 Bill Yuchen Lin, Wei Lu

Recent research efforts have shown that neural architectures can be effective in conventional information extraction tasks such as named entity recognition, yielding state-of-the-art results on standard newswire datasets.

Cross-Domain Named Entity Recognition Domain Adaptation +3

Neural Segmental Hypergraphs for Overlapping Mention Recognition

1 code implementation EMNLP 2018 Bailin Wang, Wei Lu

In this work, we propose a novel segmental hypergraph representation to model overlapping entity mentions that are prevalent in many practical datasets.

Nested Mention Recognition Nested Named Entity Recognition +1

Better Transition-Based AMR Parsing with a Refined Search Space

no code implementations EMNLP 2018 Zhijiang Guo, Wei Lu

This paper introduces a simple yet effective transition-based system for Abstract Meaning Representation (AMR) parsing.

AMR Parsing Named Entity Recognition (NER) +1

Dependency-based Hybrid Trees for Semantic Parsing

no code implementations EMNLP 2018 Zhanming Jie, Wei Lu

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations.

Semantic Parsing

Reproducible and Interpretable Spiculation Quantification for Lung Cancer Screening

1 code implementation24 Aug 2018 Wookjin Choi, Saad Nadeem, Sadegh Riyahi, Joseph O. Deasy, Allen Tannenbaum, Wei Lu

The spiculation quantification measures was then applied to the radiomics framework for pathological malignancy prediction with reproducible semi-automatic segmentation of nodule.

Learning Cross-lingual Distributed Logical Representations for Semantic Parsing

no code implementations ACL 2018 Yanyan Zou, Wei Lu

In this work, we present a study to show how learning distributed representations of the logical forms from data annotated in different languages can be used for improving the performance of a monolingual semantic parser.

Semantic Parsing

SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP)

no code implementations SEMEVAL 2018 Ph, Peter i, Amila Silva, Wei Lu

This paper describes the SemEval 2018 shared task on semantic extraction from cybersecurity reports, which is introduced for the first time as a shared task on SemEval.

Malware Detection

Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

1 code implementation ICLR 2018 Xiang Wei, Boqing Gong, Zixia Liu, Wei Lu, Liqiang Wang

Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train.

A Unified Framework for Structured Prediction: From Theory to Practice

no code implementations EMNLP 2017 Wei Lu

Based on such a framework, we show how some seemingly complicated structured prediction models such as a semantic parsing model (Lu et al., 2008; Lu, 2014) can be implemented conveniently and quickly.

AMR Parsing Chunking +3

Digital image splicing detection based on Markov features in QDCT and QWT domain

no code implementations28 Aug 2017 Ruxin Wang, Wei Lu, Shijun Xiang, Xianfeng Zhao, Jinwei Wang

In this paper, a color image splicing detection approach is proposed based on Markov transition probability of quaternion component separation in quaternion discrete cosine transform (QDCT) domain and quaternion wavelet transform (QWT) domain.

Position

Topical Coherence in LDA-based Models through Induced Segmentation

1 code implementation ACL 2017 Hesam Amoualian, Wei Lu, Eric Gaussier, Georgios Balikas, Massih R. Amini, Marianne Clausel

This paper presents an LDA-based model that generates topically coherent segments within documents by jointly segmenting documents and assigning topics to their words.

Ad-Hoc Information Retrieval General Classification +3

MalwareTextDB: A Database for Annotated Malware Articles

no code implementations ACL 2017 Swee Kiat Lim, Aldrian Obaja Muis, Wei Lu, Chen Hui Ong

Cybersecurity risks and malware threats are becoming increasingly dangerous and common.

Refutations on "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study"

2 code implementations15 May 2017 Wei Lu, Xiaokui Xiao, Amit Goyal, Keke Huang, Laks V. S. Lakshmanan

In a recent SIGMOD paper titled "Debunking the Myths of Influence Maximization: An In-Depth Benchmarking Study", Arora et al. [1] undertake a performance benchmarking study of several well-known algorithms for influence maximization.

Social and Information Networks

Rhetorical relations for information retrieval

no code implementations5 Apr 2017 Christina Lioma, Birger Larsen, Wei Lu

Typically, every part in most coherent text has some plausible reason for its presence, some function that it performs to the overall semantics of the text.

Information Retrieval Language Modelling +1

Deep neural networks for learning graph representations

no code implementations Thirtieth AAAI Conference on Artificial Intelligence 2016 Shaosheng Cao, Wei Lu, Qiongkai Xu

Different from other previous research efforts, we adopt a random surfing model to capture graph structural information directly, instead of using the sampling-based method for generating linear sequences proposed by Perozzi et al. (2014).

Clustering Denoising +1

From Competition to Complementarity: Comparative Influence Diffusion and Maximization

no code implementations1 Jul 2015 Wei Lu, Wei Chen, Laks. V. S. Lakshmanan

We study two natural optimization problems, Self Influence Maximization and Complementary Influence Maximization, in a novel setting with complementary entities.

Social and Information Networks Physics and Society H.2.8

Replicating Kernels with a Short Stride Allows Sparse Reconstructions with Fewer Independent Kernels

no code implementations17 Jun 2014 Peter F. Schultz, Dylan M. Paiton, Wei Lu, Garrett T. Kenyon

We find, for example, that for 16x16-pixel receptive fields, using eight kernels and a stride of 2 leads to sparse reconstructions of comparable quality as using 512 kernels and a stride of 16 (the nonoverlapping case).

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