Search Results for author:
Found 106 papers, 43 papers with code
Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction
Sememes are defined as the atomic units to describe the semantic meaning of concepts.
Towards Reliable and Empathetic Depression-Diagnosis-Oriented Chats
Nevertheless, the blend of task-oriented and chit-chat in diagnosis-related dialogues necessitates professional expertise and empathy.
Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind
MBS overcomes the English-centric limitations of existing methods by sampling calibration data from various languages proportionally to the language distribution of the model training datasets.
Rejection Improves Reliability: Training LLMs to Refuse Unknown Questions Using RL from Knowledge Feedback
Large Language Models (LLMs) often generate erroneous outputs, known as hallucinations, due to their limitations in discerning questions beyond their knowledge scope.
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary
In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary.
A BiRGAT Model for Multi-intent Spoken Language Understanding with Hierarchical Semantic Frames
Previous work on spoken language understanding (SLU) mainly focuses on single-intent settings, where each input utterance merely contains one user intent.
Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding
Additionally, we propose several pre-training tasks to model the interaction among text, structure, and image modalities effectively.
Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations.
A Unified Causal View of Instruction Tuning
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
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.
Seeing is not always believing: The Space of Harmless Perturbations
In the context of deep neural networks, we expose the existence of a harmless perturbation space, where perturbations leave the network output entirely unaltered.
A Comprehensive Survey on 3D Content Generation
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e. g., text, image, video, audio and 3D.
MouSi: Poly-Visual-Expert Vision-Language Models
This technique introduces a fusion network to unify the processing of outputs from different visual experts, while bridging the gap between image encoders and pre-trained LLMs.
Ranked #40 on
Visual Question Answering
on MM-Vet
Defining and Extracting generalizable interaction primitives from DNNs
Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI.
ChemDFM: Dialogue Foundation Model for Chemistry
To this end, we develop ChemDFM, the first LLM towards CGI.
FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis
Text-to-SQL, which provides zero-code interface for operating relational databases, has gained much attention in financial analysis; because, financial professionals may not well-skilled in SQL programming.
Secrets of RLHF in Large Language Models Part II: Reward Modeling
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
Text Classification Based on Knowledge Graphs and Improved Attention Mechanism
To resolve the semantic ambiguity in texts, we propose a model, which innovatively combines a knowledge graph with an improved attention mechanism.
MUST: An Effective and Scalable Framework for Multimodal Search of Target Modality
We investigate the problem of multimodal search of target modality, where the task involves enhancing a query in a specific target modality by integrating information from auxiliary modalities.
Dynamic Fault Analysis in Substations Based on Knowledge Graphs
To address the challenge of identifying hidden danger in substations from unstructured text, a novel dynamic analysis method is proposed.
ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL
Text-to-SQL aims to generate an executable SQL program given the user utterance and the corresponding database schema.
ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought
Recently Large Language Models (LLMs) have been proven to have strong abilities in various domains and tasks.
SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research
This design suffers from data leakage problem and lacks the evaluation of subjective Q/A ability.
Inducing Causal Structure for Abstractive Text Summarization
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching
Traditional unsupervised EM assumes that all entities come from two tables; however, it is more common to match entities from multiple tables in practical applications, that is, multi-table entity matching (multi-table EM).
C3: Zero-shot Text-to-SQL with ChatGPT
This paper proposes a ChatGPT-based zero-shot Text-to-SQL method, dubbed C3, which achieves 82. 3\% in terms of execution accuracy on the holdout test set of Spider and becomes the state-of-the-art zero-shot Text-to-SQL method on the Spider Challenge.
Ranked #4 on
Text-To-SQL
on spider
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
Real-time Workload Pattern Analysis for Large-scale Cloud Databases
This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis.
MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators
Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans.
Large Language Models Are Semi-Parametric Reinforcement Learning Agents
By equipping the LLM with a long-term experience memory, REMEMBERER is capable of exploiting the experiences from the past episodes even for different task goals, which excels an LLM-based agent with fixed exemplars or equipped with a transient working memory.
CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset
Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies.
Mobile-Env: An Evaluation Platform and Benchmark for LLM-GUI Interaction
A GUI task set based on WikiHow app is collected on Mobile-Env to form a benchmark covering a range of GUI interaction capabilities.
Knowledge-refined Denoising Network for Robust Recommendation
Knowledge graph (KG), which contains rich side information, becomes an essential part to boost the recommendation performance and improve its explainability.
Towards Explainable Collaborative Filtering with Taste Clusters Learning
In recent decades, there have been significant advancements in latent embedding-based CF methods for improved accuracy, such as matrix factorization, neural collaborative filtering, and LightGCN.
SEA: A Scalable Entity Alignment System
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.
HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network.
SparDL: Distributed Deep Learning Training with Efficient Sparse Communication
Recently, a few methods have been put forward to handle the SGA dilemma.
Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation
We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other and evolve together.
Unsupervised Entity Alignment for Temporal Knowledge Graphs
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
On the Structural Generalization in Text-to-SQL
Exploring the generalization of a text-to-SQL parser is essential for a system to automatically adapt the real-world databases.
Estimator: An Effective and Scalable Framework for Transportation Mode Classification over Trajectories
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.
OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue
The second phase is to fine-tune the pretrained model on the TOD data.
DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.
DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning
In this work, we aim to build a unified dialogue foundation model (DFM) which can be used to solve massive diverse dialogue tasks.
D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat
In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria.
META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs.
ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
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
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages
Recently, the structural reading comprehension (SRC) task on web pages has attracted increasing research interests.
Self-Guided Learning to Denoise for Robust Recommendation
Besides, our method can automatically switch its learning phase at the memorization point from memorization to self-guided learning, and select clean and informative memorized data via a novel adaptive denoising scheduler to improve the robustness.
HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
Furthermore, we propose a dual item embeddings design to represent and propagate collaborative signals and knowledge associations separately, and leverage the gated aggregation to distill discriminative information for better capturing user behavior patterns.
Ranked #1 on
Recommendation Systems
on Alibaba-iFashion
UniDU: Towards A Unified Generative Dialogue Understanding Framework
With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU).
MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
Inspired by the success of meta-learning on scarce training samples, we propose a novel meta-learning based framework called MetaKG, which encompasses a collaborative-aware meta learner and a knowledge-aware meta learner, to capture meta users' preference and entities' knowledge for cold-start recommendations.
Linear Array Network for Low-light Image Enhancement
However, the convolution operation is based on a local sliding window mechanism, which is difficult to construct the long-range dependencies of the feature maps.
RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark
In this paper, we investigate the real clinical fundus image restoration problem.
Deep Spatially and Temporally Aware Similarity Computation for Road Network Constrained Trajectories
Trajectory similarity computation has drawn massive attention, as it is core functionality in a wide range of applications such as ride-sharing, traffic analysis, and social recommendation.
Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
In this paper, we propose to improve prototypical networks with vector projection distance and abstract triangular Conditional Random Field (CRF) for the few-shot NLU.
FastSGD: A Fast Compressed SGD Framework for Distributed Machine Learning
Distributed ML models trained by SGD involve large amounts of gradient communication, which limits the scalability of distributed ML.
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
Machine Learning-Based Soft Sensors for Vacuum Distillation Unit
Firstly, it is important to enhance the quality of both sets of data (laboratory measurements and physical sensors) in a data pre-processing stage (as described in Methodology section).
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i. e.} the view of multi-order interactions between input variables of DNNs.
Finding Materialized Models for Model Reuse
It uses a Gaussian mixture-based metric called separation degree to rank materialized models.
Dissecting Local Properties of Adversarial Examples
Adversarial examples have attracted significant attention over the years, yet a sufficient understanding is in lack, especially when analyzing their performances in combination with adversarial training.
Copy-Move Image Forgery Detection Based on Evolving Circular Domains Coverage
The aim of this paper is to improve the accuracy of copy-move forgery detection (CMFD) in image forensics by proposing a novel scheme and the main contribution is evolving circular domains coverage (ECDC) algorithm.
Pre-treatment of outliers and anomalies in plant data: Methodology and case study of a Vacuum Distillation Unit
In this case, we used principal component analysis (PCA) with Hotelling's $T^2$ statistics to identify the long-term outliers.
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
A dual learning approach is also proposed for the utterance rewrite model to address the data sparsity problem.
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task.
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query.
A Unified Game-Theoretic Interpretation of Adversarial Robustness
This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.
LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching
Additionally, we adopt the word lattice graph as input to maintain multi-granularity information.
WebSRC: A Dataset for Web-Based Structural Reading Comprehension
In this paper, we introduce the task of structural reading comprehension (SRC) on web.
Comparison and Improvement for Delay Analysis Approaches: Theoretical Models and Experimental Tests
The test results are compared with the theoretical results, analyzed and corrected, in order to verify the feasibility of our analysis model for the performance analysis of the actual network.
Networking and Internet Architecture Performance
Searching Personalized $k$-wing in Large and Dynamic Bipartite Graphs
By exploiting the discoveries, we propose novel algorithms for maintaining the two indices, which substantially reduces the cost of maintenance.
FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems
In both letter-level and word-level attacks, our experiments show that in addition to natural appearance, FAWA achieves a 100% attack success rate with 60% less perturbations and 78% fewer iterations on average.
Optical Character Recognition
Optical Character Recognition (OCR)
An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models
Recently, pre-trained language models like BERT have shown promising performance on multiple natural language processing tasks.
SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply
In this setting, an assignment authority is to assign agents to requests such that the average idle time of the agents is minimized.
Databases Signal Processing
Structured Hierarchical Dialogue Policy with Graph Neural Networks
A novel ComNet is proposed to model the structure of a hierarchical agent.
Deep Reinforcement Learning for On-line Dialogue State Tracking
To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems.
CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking
In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history.
Dual Learning for Dialogue State Tracking
In task-oriented multi-turn dialogue systems, dialogue state refers to a compact representation of the user goal in the context of dialogue history.
Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e. g., hotel booking).
Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
Few-shot slot tagging becomes appealing for rapid domain transfer and adaptation, motivated by the tremendous development of conversational dialogue systems.
Robust Spoken Language Understanding with RL-based Value Error Recovery
The framework consists of a slot tagging model and a rule-based value error recovery module.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Neural Graph Matching Networks for Chinese Short Text Matching
Chinese short text matching usually employs word sequences rather than character sequences to get better performance.
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks
We also adopt graph attention networks with higher-order neighborhood information to encode the rich structure in AMR graphs.
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
One daunting problem for semantic parsing is the scarcity of annotation.
Jointly Encoding Word Confusion Network and Dialogue Context with BERT for Spoken Language Understanding
In this paper, a novel BERT based SLU model (WCN-BERT SLU) is proposed to encode WCNs and the dialogue context jointly.
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders
When modeling simple and complex sentences with autoencoders, we introduce different types of noise into the training process.
CrowdTSC: Crowd-based Neural Networks for Text Sentiment Classification
We propose Crowd-based neural networks for Text Sentiment Classification (CrowdTSC for short).
Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
In this paper, a novel context and schema fusion network is proposed to encode the dialogue context and schema graph by using internal and external attention mechanisms.
Ranked #8 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks
For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates.
Ranked #12 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
Index-based Solutions for Efficient Density Peak Clustering
Efficient query algorithms are proposed for these indices which significantly avoids irrelevant comparisons at the cost of space.
Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarks
Optical character recognition (OCR) is widely applied in real applications serving as a key preprocessing tool.
Optical Character Recognition
Optical Character Recognition (OCR)
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning
Experiments show that AgentGraph models significantly outperform traditional reinforcement learning approaches on most of the 18 tasks of the PyDial benchmark.
Recurrent Multi-Graph Neural Networks for Travel Cost Prediction
Origin-destination (OD) matrices are often used in urban planning, where a city is partitioned into regions and an element (i, j) in an OD matrix records the cost (e. g., travel time, fuel consumption, or travel speed) from region i to region j.
DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.
Towards Universal Dialogue State Tracking
Dialogue state tracking is the core part of a spoken dialogue system.
Structured Dialogue Policy with Graph Neural Networks
The proposed structured deep reinforcement learning is based on graph neural networks (GNN), which consists of some sub-networks, each one for a node on a directed graph.
Cost-Sensitive Active Learning for Dialogue State Tracking
Dialogue state tracking (DST), when formulated as a supervised learning problem, relies on labelled data.
Affordable On-line Dialogue Policy Learning
The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical.
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy.
On-line Dialogue Policy Learning with Companion Teaching
On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios.
