Search Results for author:
Found 99 papers, 36 papers with code
The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues
We describe a new freely available Chinese multi-party dialogue dataset for automatic extraction of dialogue-based character relationships.
Gestures Are Used Rationally: Information Theoretic Evidence from Neural Sequential Models
Verbal communication is companied by rich non-verbal signals.
Learning to Score Sign Language with Two-stage Method
Human action recognition and performance assessment have been hot research topics in recent years.
Teaching Chinese Sign Language with Feedback in Mixed Reality
Furthermore, we use mixed reality technology to construct a scenario-based 3D sign language classroom and explore the user experience of scenario teaching.
Improving Language Model Reasoning with Self-motivated Learning
The framework motivates the model itself to automatically generate rationales on existing datasets.
Toward Informal Language Processing: Knowledge of Slang in Large Language Models
Our work offers a comprehensive evaluation and a high-quality benchmark on English slang based on the OpenSubtitles corpus, serving both as a publicly accessible resource and a platform for applying tools for informal language processing.
Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants' API Invocation Capabilities
With the rise of Large Language Models (LLMs), AI assistants' ability to utilize tools, especially through API calls, has advanced notably.
The Implicit Bias of Heterogeneity towards Invariance and Causality
It is observed empirically that the large language models (LLM), trained with a variant of regression loss using numerous corpus from the Internet, can unveil causal associations to some extent.
RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection
This paper presents a robust watermark embedding scheme, named RobWE, to protect the ownership of personalized models in PFL.
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions
This work offers a hands-on reference for the research progress in deep generative models for offline policy learning, and aims to inspire improved DGM-based offline RL or IL algorithms.
MULTI: Multimodal Understanding Leaderboard with Text and Images
Rapid progress in multimodal large language models (MLLMs) highlights the need to introduce challenging yet realistic benchmarks to the academic community, while existing benchmarks primarily focus on understanding simple natural images and short context.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
Rethinking the Instruction Quality: LIFT is What You Need
Instruction tuning, a specialized technique to enhance large language model (LLM) performance via instruction datasets, relies heavily on the quality of employed data.
Accelerated Gradient Algorithms with Adaptive Subspace Search for Instance-Faster Optimization
In this paper, we open up a new way to design and analyze gradient-based algorithms with direct applications in machine learning, including linear regression and beyond.
Deep Reinforcement Learning Based Optimal Energy Management of Multi-energy Microgrids with Uncertainties
To help EMS formulate optimal dispatching schemes, a deep reinforcement learning (DRL)-based MEMG energy management scheme with renewable energy source (RES) uncertainty is proposed in this paper.
MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation
Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems.
Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
Through thorough theoretical analysis, we demonstrate that the quantum advantage in mean estimation leads to exponential advancements in regret guarantees for infinite horizon Reinforcement Learning.
RLLTE: Long-Term Evolution Project of Reinforcement Learning
We present RLLTE: a long-term evolution, extremely modular, and open-source framework for reinforcement learning (RL) research and application.
CARE: Confidence-rich Autonomous Robot Exploration using Bayesian Kernel Inference and Optimization
We first utilize Gaussian process (GP) regression to learn a surrogate model to infer the confidence-rich mutual information (CRMI) of querying control actions, then adopt an objective function consisting of predicted CRMI values and prediction uncertainties to conduct Bayesian optimization (BO), i. e., GP-based BO (GPBO).
Efficient Semi-Supervised Federated Learning for Heterogeneous Participants
Federated Learning (FL) has emerged to allow multiple clients to collaboratively train machine learning models on their private data.
OSP: Boosting Distributed Model Training with 2-stage Synchronization
However, these two types of methods can result in accuracy loss due to discarded gradients and have limited enhancement on the throughput of model synchronization, respectively.
Collaborative Optimization of Multi-microgrids System with Shared Energy Storage Based on Multi-agent Stochastic Game and Reinforcement Learning
The proposed MMG system framework can reduce energy fluctuations in the main grid by 1746. 5kW in 24 hours and achieve a cost reduction of 16. 21% in the test.
Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)
In addition, the generalization ability of the Lie group-CNN on SIM(2) on rotation-equivariance is verified on rotated-MNIST and rotated-CIFAR10, and the robustness of the network is verified on SO(2) and SE(2).
Dataset Management Platform for Machine Learning
Effective dataset management, including tasks such as data cleanup, versioning, access control, dataset transformation, automation, integrity and security, etc., can help improve the efficiency and speed of the machine learning process.
Short-term and long-term memory self-attention network for segmentation of tumours in 3D medical images
Tumour segmentation in medical images (especially 3D tumour segmentation) is highly challenging due to the possible similarity between tumours and adjacent tissues, occurrence of multiple tumours and variable tumour shapes and sizes.
PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy
Using one-shot learning to increase the creativity of pre-trained models and diversify the content of the fused images.
Deep learning for full-field ultrasonic characterization
This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform for distributed reconstruction of mechanical properties in layered components from full waveform data.
An Instrumental Variable Approach to Confounded Off-Policy Evaluation
Off-policy evaluation (OPE) is a method for estimating the return of a target policy using some pre-collected observational data generated by a potentially different behavior policy.
Quantile Off-Policy Evaluation via Deep Conditional Generative Learning
Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy.
Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning
Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data.
MOB-FL: Mobility-Aware Federated Learning for Intelligent Connected Vehicles
Federated learning (FL) is a promising approach to enable the future Internet of vehicles consisting of intelligent connected vehicles (ICVs) with powerful sensing, computing and communication capabilities.
Improving Performance of Automatic Keyword Extraction (AKE) Methods Using PoS-Tagging and Enhanced Semantic-Awareness
Automatic keyword extraction (AKE) has gained more importance with the increasing amount of digital textual data that modern computing systems process.
ReAFFPN: Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection
This paper proposes a Rotation-equivariant Attention Feature Fusion Pyramid Networks for Aerial Object Detection named ReAFFPN.
Tracing Semantic Variation in Slang
However, slang semantic variation is not well understood and under-explored in the natural language processing of slang.
Optimization of rule-based energy management strategies for hybrid vehicles using dynamic programming
The popular vehicle dynamic model used in many energy management optimization studies does not capture the vehicle dynamics that the in-vehicle measurement system does.
KE-QI: A Knowledge Enhanced Article Quality Identification Dataset
With so many articles of varying qualities being produced every moment, it is a very urgent task to screen outstanding articles and commit them to social media.
Crosslinguistic word order variation reflects evolutionary pressures of dependency and information locality
Using data from 80 languages in 17 language families and phylogenetic modeling, we demonstrate that languages evolve to balance these pressures, such that word order change is accompanied by change in the frequency distribution of the syntactic structures which speakers communicate to maintain overall efficiency.
Language Anisotropic Cross-Lingual Model Editing
On the newly defined cross-lingual model editing task, we empirically demonstrate the failure of monolingual baselines in propagating the edit to multiple languages and the effectiveness of the proposed language anisotropic model editing.
Noun2Verb: Probabilistic frame semantics for word class conversion
We present a formal framework, Noun2Verb, that simulates the production and comprehension of novel denominal verb usages by modeling shared knowledge of speaker and listener in semantic frames.
Semantically Informed Slang Interpretation
Slang is a predominant form of informal language making flexible and extended use of words that is notoriously hard for natural language processing systems to interpret.
Image Captioning In the Transformer Age
This drawback inspires the researchers to develop a homogeneous architecture that facilitates end-to-end training, for which Transformer is the perfect one that has proven its huge potential in both vision and language domains and thus can be used as the basic component of the visual encoder and language decoder in an IC pipeline.
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Combinatorial optimization is a well-established area in operations research and computer science.
Neural reality of argument structure constructions
Second, in a "Jabberwocky" priming-based experiment, we find that LMs associate ASCs with meaning, even in semantically nonsensical sentences.
Improving short-term bike sharing demand forecast through an irregular convolutional neural network
As an important task for the management of bike sharing systems, accurate forecast of travel demand could facilitate dispatch and relocation of bicycles to improve user satisfaction.
HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis
Contextualized word embeddings have demonstrated state-of-the-art performance in various natural language processing tasks including those that concern historical semantic change.
ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation
The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models.
Nonlinear Intensity Underwater Sonar Image Matching Method Based on Phase Information and Deep Convolution Features
In the field of deep-sea exploration, sonar is presently the only efficient long-distance sensing device.
Breaking the curse of dimensionality with Isolation Kernel
The curse of dimensionality has been studied in different aspects.
Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining
Natural language relies on a finite lexicon to express an unbounded set of emerging ideas.
An unsupervised framework for tracing textual sources of moral change
Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time.
Evolution of emotion semantics
This consensus may give the impression that their meaning is static, but we propose this is not the case.
What do writing features tell us about AI papers?
As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention.
Measuring Financial Time Series Similarity With a View to Identifying Profitable Stock Market Opportunities
Forecasting stock returns is a challenging problem due to the highly stochastic nature of the market and the vast array of factors and events that can influence trading volume and prices.
SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems
Recently deep neural networks (DNNs) have achieved tremendous success for object detection in overhead (e. g., satellite) imagery.
A diachronic evaluation of gender asymmetry in euphemism
We assembled a list of 106 euphemism-taboo pairs to analyze their relative use through time by each gender in the corpora.
How is BERT surprised? Layerwise detection of linguistic anomalies
Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly.
Integration of Unpaired Single-cell Chromatin Accessibility and Gene Expression Data via Adversarial Learning
Deep learning has empowered analysis for single-cell sequencing data in many ways and has generated deep understanding about a range of complex cellular systems.
A Computational Framework for Slang Generation
Slang is a common type of informal language, but its flexible nature and paucity of data resources present challenges for existing natural language systems.
Self Sparse Generative Adversarial Networks
In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem.
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents.
Ranked #1 on
Key Information Extraction
on SROIE
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition
We tackle implicit discourse relation recognition.
Semantic coordinates analysis reveals language changes in the AI field
Semantic shifts can reflect changes in beliefs across hundreds of years, but it is less clear whether trends in fast-changing communities across a short time can be detected.
A robust low data solution: dimension prediction of semiconductor nanorods
Deep neural network is further applied to develop regression model which demonstrated the well performed prediction on both the original and generated data with a similar distribution.
Inferring symmetry in natural language
Our results show that a hybrid transfer learning model that integrates linguistic features with contextualized language models most faithfully predicts the empirical data.
Word class flexibility: A deep contextualized approach
Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories.
Contextualized moral inference
Our methodology builds on recent work in contextualized language models and textual inference of moral sentiment.
Improving probability selecting based weights for Satisfiability Problem
SelectNTS is an improved probability selecting based local search algorithm for SAT problem.
A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems
Moreover, its gradient complexity to obtain an $\varepsilon$-stationary point of the objective function is bounded by $\mathcal{O}\left( \varepsilon ^{-2} \right)$ (resp., $\mathcal{O}\left( \varepsilon ^{-4} \right)$) under the strongly convex-nonconcave (resp., convex-nonconcave) setting.
MultiXNet: Multiclass Multistage Multimodal Motion Prediction
One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future.
The Typology of Polysemy: A Multilingual Distributional Framework
Lexical semantic typology has identified important cross-linguistic generalizations about the variation and commonalities in polysemy patterns---how languages package up meanings into words.
Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia
Chinese dynastic histories form a large continuous linguistic space of approximately 2000 years, from the 3rd century BCE to the 18th century CE.
Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation
Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations.
A Computational Investigation on Denominalization
Language has been a dynamic system and word meanings always have been changed over times.
Application of Pre-training Models in Named Entity Recognition
Then, we apply these pre-training models to a NER task by fine-tuning, and compare the effects of the different model architecture and pre-training tasks on the NER task.
Text-based inference of moral sentiment change
We present a text-based framework for investigating moral sentiment change of the public via longitudinal corpora.
Slang Detection and Identification
The prevalence of informal language such as slang presents challenges for natural language systems, particularly in the automatic discovery of flexible word usages.
HIT-SCIR at MRP 2019: A Unified Pipeline for Meaning Representation Parsing via Efficient Training and Effective Encoding
This paper describes our system (HIT-SCIR) for CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing.
Ranked #1 on
UCCA Parsing
on CoNLL 2019
Treat the Word As a Whole or Look Inside? Subword Embeddings Model Language Change and Typology
We use a variant of word embedding model that incorporates subword information to characterize the degree of compositionality in lexical semantics.
Fourier-based Rotation-invariant Feature Boosting: An Efficient Framework for Geospatial Object Detection
To this end, we propose a novel and efficient framework for geospatial object detection in this letter, called Fourier-based rotation-invariant feature boosting (FRIFB).
Automated Essay Scoring based on Two-Stage Learning
Current state-of-art feature-engineered and end-to-end Automated Essay Score (AES) methods are proven to be unable to detect adversarial samples, e. g. the essays composed of permuted sentences and the prompt-irrelevant essays.
C2TCP: A Flexible Cellular TCP to Meet Stringent Delay Requirements
Since current widely available network protocols/systems are mainly throughput-oriented designs, meeting stringent delay requirements of new applications such as virtual reality and vehicle-to-vehicle communications on cellular network requires new network protocol/system designs.
Networking and Internet Architecture
Is Nike female? Exploring the role of sound symbolism in predicting brand name gender
Are brand names such as Nike female or male?
Using active learning to expand training data for implicit discourse relation recognition
We tackle discourse-level relation recognition, a problem of determining semantic relations between text spans.
Incorporating Image Matching Into Knowledge Acquisition for Event-Oriented Relation Recognition
In particular, we incorporate image processing into the acquisition of similar event instances, including the utilization of images for visually representing event scenes, and the use of the neural network based image matching for approximate calculation between events.
Cellular Controlled Delay TCP (C2TCP)
To cope with these challenges, we present C2TCP, a flexible end-to-end solution targeting interactive applications requiring high throughput and low delay in cellular networks.
Networking and Internet Architecture
Incorporating Latent Meanings of Morphological Compositions to Enhance Word Embeddings
Experiments on word similarity, syntactic analogy and text classification are conducted to validate the feasibility of our models.
Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power
Linguistic alignment between dialogue partners has been claimed to be affected by their relative social power.
Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance
We propose a perspective on dialogue that focuses on relative information contributions of conversation partners as a key to successful communication.
Redefinition of the concept of fuzzy set based on vague partition from the perspective of axiomatization
Based on the in-depth analysis of the essence and features of vague phenomena, this paper focuses on establishing the axiomatical foundation of membership degree theory for vague phenomena, presents an axiomatic system to govern membership degrees and their interconnections.
Implicitly Incorporating Morphological Information into Word Embedding
In this paper, we propose three novel models to enhance word embedding by implicitly using morphological information.
Graph Regularized Non-negative Matrix Factorization By Maximizing Correntropy
Non-negative matrix factorization (NMF) has proved effective in many clustering and classification tasks.
Inference and communication in the game of Password
Second, we predict that speakers and hearers are calibrated, and that both make accurate assumptions about the strategy used by the other.
