Search Results for author:
Found 79 papers, 47 papers with code
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Instance-adaptive training with noise-robust losses against noisy labels
In order to alleviate the huge demand for annotated datasets for different tasks, many recent natural language processing datasets have adopted automated pipelines for fast-tracking usable data.
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution
Coreference resolution over semantic graphs like AMRs aims to group the graph nodes that represent the same entity.
Harder Tasks Need More Experts: Dynamic Routing in MoE Models
In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input difficulty.
Probing Multimodal Large Language Models for Global and Local Semantic Representations
The advancement of Multimodal Large Language Models (MLLMs) has greatly accelerated the development of applications in understanding integrated texts and images.
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos.
Ranked #57 on
Visual Question Answering
on MM-Vet
A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models
While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations.
Exploring the Usage of Chinese Pinyin in Pretraining
Through delicate pretraining tasks, the characters and pinyin representation are fused, which can enhance the error tolerance for SSP errors.
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read.
Semantic optical fiber communication system
The current optical communication systems minimize bit or symbol errors without considering the semantic meaning behind digital bits, thus transmitting a lot of unnecessary information.
PaletteNeRF: Palette-based Color Editing for NeRFs
Instead of predicting pixel colors as in vanilla NeRFs, our method predicts additive weights.
Learning a Grammar Inducer from Massive Uncurated Instructional Videos
While previous work focuses on building systems for inducing grammars on text that are well-aligned with video content, we investigate the scenario, in which text and video are only in loose correspondence.
Neural Color Operators for Sequential Image Retouching
The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar.
Discourse-Aware Graph Networks for Textual Logical Reasoning
In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation
Graph contrastive learning (GCL), as a popular approach to graph self-supervised learning, has recently achieved a non-negligible effect.
Distant finetuning with discourse relations for stance classification
Approaches for the stance classification task, an important task for understanding argumentation in debates and detecting fake news, have been relying on models which deal with individual debate topics.
Zero-shot Cross-lingual Conversational Semantic Role Labeling
While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training.
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding.
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks.
Exophoric Pronoun Resolution in Dialogues with Topic Regularization
Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem.
Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging
In this paper, inspired by the untrained neural networks such as deep image priors (DIP) and deep decoders, we develop a framework by integrating DIP into the plug-and-play regime, leading to a self-supervised network for spectral SCI reconstruction.
Principle-driven Fiber Transmission Model based on PINN Neural Network
Instead of adopting input signals and output signals which are calculated by SSFM algorithm in advance before training, this principle-driven PINN based fiber model adopts frames of time and distance as its inputs and the corresponding real and imaginary parts of NLSE solutions as its outputs.
On the Generation of Medical Dialogs for COVID-19
Training complex dialog generation models on small datasets bears high risk of overfitting.
TexSmart: A System for Enhanced Natural Language Understanding
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Do Boat and Ocean Suggest Beach? Dialogue Summarization with External Knowledge
To evaluate the inference capability of different methods, we also propose a new evaluation metric based on CODC.
Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment
The first LA-GCN module constructs an aesthetics-related graph in the coordinate space and performs reasoning over spatial nodes.
Domain-Adaptive Pretraining Methods for Dialogue Understanding
Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks.
Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization
Our results show that learning algorithms with the consistent univariate loss have an error bound of $O(c)$ ($c$ is the number of labels), while algorithms with the inconsistent pairwise loss depend on $O(\sqrt{c})$ as shown in prior work.
Conversational Semantic Role Labeling
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence.
Video-aided Unsupervised Grammar Induction
We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video.
GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
Graph Neural Networks (GNNs) have recently shown to be powerful tools for representing and analyzing graph data.
Structural Information Preserving for Graph-to-Text Generation
The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs.
Ranked #10 on
Data-to-Text Generation
on WebNLG
Joint Coreference Resolution and Character Linking for Multiparty Conversation
Character linking, the task of linking mentioned people in conversations to the real world, is crucial for understanding the conversations.
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Robust Dialogue Utterance Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable.
Bi-level Score Matching for Learning Energy-based Latent Variable Models
This paper presents a bi-level score matching (BiSM) method to learn EBLVMs with general structures by reformulating SM as a bi-level optimization problem.
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter
For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance.
Efficient Learning of Generative Models via Finite-Difference Score Matching
Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
Our core innovation is the learning of a region-phrase score function, based on which an image-sentence score function is further constructed.
ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT
Zero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively.
A Survey of Adversarial Learning on Graphs
To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically.
On the Role of Conceptualization in Commonsense Knowledge Graph Construction
Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs as they consist of much larger number of nodes formed by loosely-structured text, which, though, enables them to handle highly diverse queries in natural language related to commonsense, leads to unique challenges for automatic KG construction methods.
Boosting Adversarial Training with Hypersphere Embedding
Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models.
Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment
Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity.
Multiplex Word Embeddings for Selectional Preference Acquisition
Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.
Triple Generative Adversarial Networks
It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).
Scalable Global Alignment Graph Kernel Using Random Features: From Node Embedding to Graph Embedding
In particular, RGE is shown to achieve \emph{(quasi-)linear scalability} with respect to the number and the size of the graphs.
Efficient Global String Kernel with Random Features: Beyond Counting Substructures
In this paper, we present a new class of global string kernels that aims to (i) discover global properties hidden in the strings through global alignments, (ii) maintain positive-definiteness of the kernel, without introducing a diagonal dominant kernel matrix, and (iii) have a training cost linear with respect to not only the length of the string but also the number of training string samples.
Understanding and Stabilizing GANs' Training Dynamics with Control Theory
There are existing efforts that model the training dynamics of GANs in the parameter space but the analysis cannot directly motivate practically effective stabilizing methods.
Ranked #37 on
Image Generation
on CIFAR-10
(Inception score metric)
Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks
Our experiments on CIFAR-10 and CIFAR-100 demonstrate that MI can further improve the adversarial robustness for the models trained by mixup and its variants.
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously.
Efficient training and design of photonic neural network through neuroevolution
Recently, optical neural networks (ONNs) integrated in photonic chips has received extensive attention because they are expected to implement the same pattern recognition tasks in the electronic platforms with high efficiency and low power consumption.
Multi-Granular Text Encoding for Self-Explaining Categorization
Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence.
Multi-objects Generation with Amortized Structural Regularization
Deep generative models (DGMs) have shown promise in image generation.
Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering
However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.
Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e. g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models.
Lattice CNNs for Matching Based Chinese Question Answering
Short text matching often faces the challenges that there are great word mismatch and expression diversity between the two texts, which would be further aggravated in languages like Chinese where there is no natural space to segment words explicitly.
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers
Most approaches to extraction multiple relations from a paragraph require multiple passes over the paragraph.
Ranked #19 on
Relation Extraction
on SemEval-2010 Task-8
Improving Adversarial Robustness via Promoting Ensemble Diversity
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks.
To Relieve Your Headache of Training an MRF, Take AdVIL
We propose a black-box algorithm called {\it Adversarial Variational Inference and Learning} (AdVIL) to perform inference and learning on a general Markov random field (MRF).
From Node Embedding to Graph Embedding: Scalable Global Graph Kernel via Random Features
Graph kernels are one of the most important methods for graph data analysis and have been successfully applied in diverse applications.
Word Mover's Embedding: From Word2Vec to Document Embedding
While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings.
SQL-to-Text Generation with Graph-to-Sequence Model
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.
Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Existing neural semantic parsers mainly utilize a sequence encoder, i. e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees.
Learning Implicit Generative Models by Teaching Explicit Ones
Implicit generative models are difficult to train as no explicit density functions are defined.
Deep Structured Generative Models
Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures.
Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.
Ranked #1 on
SQL-to-Text
on WikiSQL
Fifth order finite volume WENO in general orthogonally-curvilinear coordinates
A scheme for calculating the linear weights, optimal weights, and smoothness indicator on a regularly- and irregularly-spaced grid in orthogonally-curvilinear coordinates is proposed.
Computational Physics
The YouTube-8M Kaggle Competition: Challenges and Methods
We took part in the YouTube-8M Video Understanding Challenge hosted on Kaggle, and achieved the 10th place within less than one month's time.
Triple Generative Adversarial Nets
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL).
Hybrid Question Answering over Knowledge Base and Free Text
While these systems are able to provide more precise answers than information retrieval (IR) based QA systems, the natural incompleteness of KB inevitably limits the question scope that the system can answer.
Question Answering on Freebase via Relation Extraction and Textual Evidence
Existing knowledge-based question answering systems often rely on small annotated training data.
Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling
Syntactic features play an essential role in identifying relationship in a sentence.
Ranked #3 on
Relation Classification
on SemEval 2010 Task 8
