Search Results for author:
Found 126 papers, 47 papers with code
Effect Generation Based on Causal Reasoning
Given an input cause sentence, a causal subgraph is retrieved from the event causality network and is encoded with the graph attention mechanism, in order to support better reasoning of the potential effects.
Event Graph based Sentence Fusion
Sentence fusion is a conditional generation task that merges several related sentences into a coherent one, which can be deemed as a summary sentence.
MMCoQA: Conversational Question Answering over Text, Tables, and Images
In this paper, we hence define a novel research task, i. e., multimodal conversational question answering (MMCoQA), aiming to answer users’ questions with multimodal knowledge sources via multi-turn conversations.
JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer
Moreover, we adopt a two-stage learning strategy for skill-aware recommendation, in which we utilize the skill distribution to guide JD representation learning in the recall stage, and then combine the user profiles for final prediction in the ranking stage.
Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue
Inspired by decision-making theories in cognitive science, we propose a novel target-constrained bidirectional planning (TRIP) approach, which plans an appropriate dialogue path by looking ahead and looking back.
ICON: Improving Inter-Report Consistency of Radiology Report Generation via Lesion-aware Mix-up Augmentation
Previous research on radiology report generation has made significant progress in terms of increasing the clinical accuracy of generated reports.
Distillation Enhanced Generative Retrieval
Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target.
Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond
Building upon this capability, we propose to enable multimodal large language models (MLLMs) to memorize and recall images within their parameters.
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
Tuning pretrained language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents.
Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference.
Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis
Clinicians typically employ both intuitive and analytic reasoning to formulate a differential diagnosis.
Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
An emotional support conversation system aims to alleviate users' emotional distress and assist them in addressing their challenges.
The Critique of Critique
In this paper, we pioneer the critique of critique, termed MetaCritique, which is a framework to evaluate the critique from two aspects, i. e., factuality as precision score and comprehensiveness as recall score.
How Far Are We from Believable AI Agents? A Framework for Evaluating the Believability of Human Behavior Simulation
Human behavior simulation of AI agents necessitates the agents to possess a quality of believability, which is crucial as it facilitates users in establishing trust toward the agents and streamlines the fulfillment of the agents' goal.
Evolving Large Language Model Assistant with Long-Term Conditional Memory
It focuses on preserving the knowledge and experience from the history dialogue between the user and AI assistant, which can be applied to future dialogue for generating a better response.
COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
We achieve a biomedical multilingual corpus by incorporating three granularity knowledge alignments (entity, fact, and passage levels) into monolingual corpora.
Personalized Federated X -armed Bandit
In this work, we study the personalized federated $\mathcal{X}$-armed bandit problem, where the heterogeneous local objectives of the clients are optimized simultaneously in the federated learning paradigm.
RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning
It then combines the historical records, spatiotemporal information, and radiographs for report generation, where a disease progression graph and dynamic progression reasoning mechanism are devised to accurately select the attributes of each observation and progression.
VIBE: Topic-Driven Temporal Adaptation for Twitter Classification
Language features are evolving in real-world social media, resulting in the deteriorating performance of text classification in dynamics.
Self-Detoxifying Language Models via Toxification Reversal
Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers.
Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation
Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversational AI.
Aligning Language Models with Human Preferences via a Bayesian Approach
For this alignment, current popular methods leverage a reinforcement learning (RL) approach with a reward model trained on feedback from humans.
Survey on Deep Face Restoration: From Non-blind to Blind and Beyond
We also discuss notable benchmarks commonly utilized in the field.
Comparing Forward and Inverse Design Paradigms: A Case Study on Refractory High-Entropy Alloys
The rapid design of advanced materials is a topic of great scientific interest.
Learning to Rank in Generative Retrieval
However, only learning to generate is insufficient for generative retrieval.
ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning
This paper explores the task of radiology report generation, which aims at generating free-text descriptions for a set of radiographs.
Medical Dialogue Generation via Dual Flow Modeling
It extracts the medical entities and dialogue acts used in the dialogue history and models their transitions with an entity-centric graph flow and a sequential act flow, respectively.
Multiview Identifiers Enhanced Generative Retrieval
Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target.
Theoretically Principled Federated Learning for Balancing Privacy and Utility
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility.
Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue
The key to achieving this task lies in planning dialogue paths that smoothly and coherently direct conversations towards the target.
CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Structure for Vision-Language Retrieval
To address this challenge, in this paper, we experimentally observe that the vision-language divergence may cause the existence of strong and weak modalities, and the hard cross-modal consistency cannot guarantee that strong modal instances' relationships are not affected by weak modality, resulting in the strong modal instances' relationships perturbed despite learned consistent representations. To this end, we propose a novel and directly Coordinated VisionLanguage Retrieval method (dubbed CoVLR), which aims to study and alleviate the desynchrony problem between the cross-modal alignment and single-modal cluster-preserving tasks.
A Game-theoretic Framework for Privacy-preserving Federated Learning
To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks.
PyXAB -- A Python Library for $\mathcal{X}$-Armed Bandit and Online Blackbox Optimization Algorithms
We introduce a Python open-source library for $\mathcal{X}$-armed bandit and online blackbox optimization named PyXAB.
Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data.
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans.
Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network
Recently, great progress has been made in single-image super-resolution (SISR) based on deep learning technology.
COLA: Improving Conversational Recommender Systems by Collaborative Augmentation
Inspired by collaborative filtering, we propose a collaborative augmentation (COLA) method to simultaneously improve both item representation learning and user preference modeling to address these issues.
Few-shot Query-Focused Summarization with Prefix-Merging
Drawn inspiration from prefix-tuning, we are allowed to integrate the task knowledge from text summarization and question answering into a properly designed prefix and apply the merged prefix to query-focused summarization.
Always Valid Risk Monitoring for Online Matrix Completion
Always-valid concentration inequalities are increasingly used as performance measures for online statistical learning, notably in the learning of generative models and supervised learning.
CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation
Recent approaches to empathetic response generation incorporate emotion causalities to enhance comprehension of both the user's feelings and experiences.
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
Providing Emotional Support (ES) to soothe people in emotional distress is an essential capability in social interactions.
Vertical Semi-Federated Learning for Efficient Online Advertising
Specifically, we build an inference-efficient single-party student model applicable to the whole sample space and meanwhile maintain the advantage of the federated feature extension.
Modeling Content-Emotion Duality via Disentanglement for Empathetic Conversation
To solve the task, it is essential to model the content-emotion duality of a dialogue, which is composed of the content view (i. e., what personal experiences are described) and the emotion view (i. e., the feelings of the speaker on these experiences).
Addressing Token Uniformity in Transformers via Singular Value Transformation
In this paper, we propose to use the distribution of singular values of outputs of each transformer layer to characterise the phenomenon of token uniformity and empirically illustrate that a less skewed singular value distribution can alleviate the `token uniformity' problem.
Visual Subtitle Feature Enhanced Video Outline Generation
Furthermore, based on the similarity between video outlines and textual outlines, we use a large number of articles with chapter headings to pretrain our model.
Revising Image-Text Retrieval via Multi-Modal Entailment
While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from fitting other images.
Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems
Recommendation dialogue systems aim to build social bonds with users and provide high-quality recommendations.
Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution
Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction.
VFed-SSD: Towards Practical Vertical Federated Advertising
As an emerging secure learning paradigm in lever-aging cross-agency private data, vertical federatedlearning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher.
Federated X-Armed Bandit
This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global optimum.
A Coupling Enhancement Algorithm for ZrO2 Ceramic Bearing Ball Surface Defect Detection Based on Cartoon-texture Decomposition Model and Multi-Scale Filtering Method
The experimental results show that the image denoising method of ZrO2 ceramic bearing ball surface defect based on cartoon-texture decomposition model can denoise while retaining the image details.
"My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics
In this paper, we explore how to bring interpretability to data-driven DSMD.
Lightweight Bimodal Network for Single-Image Super-Resolution via Symmetric CNN and Recursive Transformer
Single-image super-resolution (SISR) has achieved significant breakthroughs with the development of deep learning.
Federated Online Sparse Decision Making
This paper presents a novel federated linear contextual bandits model, where individual clients face different K-armed stochastic bandits with high-dimensional decision context and coupled through common global parameters.
Feature Distillation Interaction Weighting Network for Lightweight Image Super-Resolution
Convolutional neural networks based single-image super-resolution (SISR) has made great progress in recent years.
CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data.
Ranked #3 on
Scene Flow Estimation
on Spring
Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality
Empathetic response generation aims to comprehend the user emotion and then respond to it appropriately.
A Systematic Survey of Deep Learning-based Single-Image Super-Resolution
This is an exhaustive survey of SISR, which can help researchers better understand SISR and inspire more exciting research in this field.
Deep Dirichlet Process Mixture Models
In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning.
Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization
During the training stage, with teacher forcing these models are optimized to maximize the likelihood of the gold summary given the gold summary tokens as input to the decoder, while at inference the given tokens are replaced by the generated tokens.
PolyU CBS-Comp at SemEval-2021 Task 1: Lexical Complexity Prediction (LCP)
In this contribution, we describe the system presented by the PolyU CBS-Comp Team at the Task 1 of SemEval 2021, where the goal was the estimation of the complexity of words in a given sentence context.
Optimum-statistical Collaboration Towards General and Efficient Black-box Optimization
In this paper, we make the key delineation on the roles of resolution and statistical uncertainty in hierarchical bandits-based black-box optimization algorithms, guiding a more general analysis and a more efficient algorithm design.
A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering
Moreover, in order to collect more complementary information in the historical context, we also propose to incorporate the multi-round relevance feedback technique to explore the impact of the retrieval context on current question understanding.
Conversational Question Answering
Open-Domain Question Answering
+1
Data Distillation for Text Classification
In this paper, we study a related but orthogonal issue, data distillation, which aims to distill the knowledge from a large training dataset down to a smaller and synthetic one.
A Simple Unified Framework for High Dimensional Bandit Problems
Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery.
Incremental Knowledge Based Question Answering
In the past years, Knowledge-Based Question Answering (KBQA), which aims to answer natural language questions using facts in a knowledge base, has been well developed.
On the Marginal Regret Bound Minimization of Adaptive Methods
Numerous adaptive algorithms such as AMSGrad and Radam have been proposed and applied to deep learning recently.
Variance Reduction on General Adaptive Stochastic Mirror Descent
In this work, we investigate the idea of variance reduction by studying its properties with general adaptive mirror descent algorithms in nonsmooth nonconvex finite-sum optimization problems.
Stochastic Deep Gaussian Processes over Graphs
In this paper we propose Stochastic Deep Gaussian Processes over Graphs (DGPG), which are deep structure models that learn the mappings between input and output signals in graph domains.
Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT
We also introduce a hierarchical structure, which incorporates the multi-level of granularities of the textual information into the model.
MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation
To push forward the future research on building expert-sensitive medical dialogue system, we proposes two kinds of medical dialogue tasks based on MedDG dataset.
Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech
Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre.
Increased-confidence adversarial examples for deep learning counter-forensics
Transferability of adversarial examples is a key issue to apply this kind of attacks against multimedia forensics (MMF) techniques based on Deep Learning (DL) in a real-life setting.
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
How Does BN Increase Collapsed Neural Network Filters?
This phenomenon is caused by the normalization effect of BN, which induces a non-trainable region in the parameter space and reduces the network capacity as a result.
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
Semantic parsing aims to transform natural language (NL) utterances into formal meaning representations (MRs), whereas an NL generator achieves the reverse: producing a NL description for some given MRs.
Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems
Here we propose Knowledge-aware Graph Neural Networks with Label Smoothness regularization (KGNN-LS) to provide better recommendations.
Ranked #1 on
Recommendation Systems
on Dianping-Food
Knowledge Graph Convolutional Networks for Recommender Systems
To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information.
Ranked #1 on
Click-Through Rate Prediction
on Book-Crossing
When Collaborative Filtering Meets Reinforcement Learning
In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations.
Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation
Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems.
Visual-Texual Emotion Analysis with Deep Coupled Video and Danmu Neural Networks
To enhance the emotion discriminativeness of words in textual feature extraction, we propose Emotional Word Embedding (EWE) to learn text representations by jointly considering their semantics and emotions.
Meta-path Augmented Response Generation
We propose a chatbot, namely Mocha to make good use of relevant entities when generating responses.
Variational Autoregressive Decoder for Neural Response Generation
Combining the virtues of probability graphic models and neural networks, Conditional Variational Auto-encoder (CVAE) has shown promising performance in applications such as response generation.
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems.
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization
Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably.
Ranked #23 on
Text Summarization
on GigaWord
Large scale classification in deep neural network with Label Mapping
Therefore, it is infeasible to solve the multi-class classification problem using deep neural network when the number of classes are huge.
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
We evaluate our approach on two review datasets, Yelp and Amazon.
Ranked #6 on
Unsupervised Text Style Transfer
on Yelp
RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance.
Ranked #2 on
Click-Through Rate Prediction
on Book-Crossing
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.
Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
The decoding of the complex structure model is regularized by the additionally trained simple structure model.
Faithful to the Original: Fact Aware Neural Abstractive Summarization
While previous abstractive summarization approaches usually focus on the improvement of informativeness, we argue that faithfulness is also a vital prerequisite for a practical abstractive summarization system.
Ranked #22 on
Text Summarization
on GigaWord
DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
We develop a high-quality multi-turn dialog dataset, DailyDialog, which is intriguing in several aspects.
Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering
The new clustering method is easy to use and consistently outperforms other methods on a variety of data sets.
Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization
In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization.
A Conditional Variational Framework for Dialog Generation
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.
Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
Despite the successes in capturing continuous distributions, the application of generative adversarial networks (GANs) to discrete settings, like natural language tasks, is rather restricted.
Mode Regularized Generative Adversarial Networks
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes.
Content-based Influence Modeling for Opinion Behavior Prediction
The advantages of the proposed model is the ability to handle the semantic information and to learn two influence components including the opinion influence of the content information and the social relation factors.
Joint Copying and Restricted Generation for Paraphrase
In this paper, we develop a novel Seq2Seq model to fuse a copying decoder and a restricted generative decoder.
Improving Multi-Document Summarization via Text Classification
Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents.
Emotion Corpus Construction Based on Selection from Hashtags
Secondly, a SVM based classifier is used to select the data whose natural labels are consistent with the predicted labels.
AttSum: Joint Learning of Focusing and Summarization with Neural Attention
Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization.
TGSum: Build Tweet Guided Multi-Document Summarization Dataset
Both informativeness and readability of the collected summaries are verified by manual judgment.
Component-Enhanced Chinese Character Embeddings
Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English.
A Confident Information First Principle for Parametric Reduction and Model Selection of Boltzmann Machines
We then revisit Boltzmann machines (BM) from a model selection perspective and theoretically show that both the fully visible BM (VBM) and the BM with hidden units can be derived from the general binary multivariate distribution using the CIF principle.
Understanding Boltzmann Machine and Deep Learning via A Confident Information First Principle
Typical dimensionality reduction methods focus on directly reducing the number of random variables while retaining maximal variations in the data.
