Search Results for author:
Found 112 papers, 28 papers with code
Modeling Content Importance for Summarization with Pre-trained Language Models
Previous work is mostly based on statistical methods that estimate word-level salience, which does not consider semantics and larger context when quantifying importance.
Temporal Logic Point Processes
We propose a modeling framework for event data, which excels in small data regime with the ability to incorporate domain knowledge.
On-device Real-time Custom Hand Gesture Recognition
Our framework provides a pre-trained single-hand embedding model that can be fine-tuned for custom gesture recognition.
Latent Degradation Representation Constraint for Single Image Deraining
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining.
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to an external modus operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning capacities.
Exploring Demonstration Ensembling for In-context Learning
The standard approach for ICL is to prompt the LM with concatenated demonstrations followed by the test input.
Reinforcement Logic Rule Learning for Temporal Point Processes
Leveraging the temporal point process modeling and learning framework, the rule content and weights will be gradually optimized until the likelihood of the observational event sequences is optimal.
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first.
Spatio-Temporal Classification of Lung Ventilation Patterns using 3D EIT Images: A General Approach for Individualized Lung Function Evaluation
A simple convolutional neural network is used for classification.
Diffusion Model Based Low-Light Image Enhancement for Space Satellite
In this article, we propose a data-driven method for low-light image enhancement (LLIE) of spin targets in space environment based on diffusion model.
Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations
Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations.
Discriminator-Guided Multi-step Reasoning with Language Models
In the context of multi-step reasoning, language models (LMs) probabilities are often miscalibrated -- solutions with high probabilities are not always correct.
Meta-review Generation with Checklist-guided Iterative Introspection
Opinions in the scientific domain can be divergent, leading to controversy or consensus among reviewers.
You Are What You Annotate: Towards Better Models through Annotator Representations
Annotator disagreement is ubiquitous in natural language processing (NLP) tasks.
AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content
Long document summarization systems are critical for domains with lengthy and jargonladen text, yet they present significant challenges to researchers and developers with limited computing resources.
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average since there is no specific knowledge in it.
Introspective Tips: Large Language Model for In-Context Decision Making
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.
BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints.
Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection
Thus, virtual simulation experiments can provide a solution to this challenge.
Implementing Active Learning in Cybersecurity: Detecting Anomalies in Redacted Emails
In this paper we present research results concerning the application of Active Learning to anomaly detection in redacted emails, comparing the utility of different methods for implementing active learning in this context.
Conservative State Value Estimation for Offline Reinforcement Learning
In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalty on OOD states.
The diagnostic utility of endocytoscopy for the detection of esophageal lesions: a systematic review and meta-analysis
Objective: To systematically evaluate the value of endocytoscopy (ECS) in the diagnosis of early esophageal cancer (EC).
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
To address these two limitations, this paper formulates the oversubscription for cloud as a chance-constrained optimization problem and propose an effective Chance Constrained Multi-Agent Reinforcement Learning (C2MARL) method to solve this problem.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
Generative models have demonstrated impressive results on Aspect-based Sentiment Analysis (ABSA) tasks, particularly for the emerging task of extracting Aspect-Category-Opinion-Sentiment (ACOS) quadruples.
Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis
In this work, we introduce the task of multimodal ideology prediction, where a model predicts binary or five-point scale ideological leanings, given a text-image pair with political content.
Time-aware Prompting for Text Generation
Despite having less performance drop when testing on data drawn from a later time, linear prompts focus more on non-temporal information and are less sensitive to the given timestamps, according to human evaluations and sensitivity analyses.
Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation
We present a novel generative framework to allow the generation of canonical names for entities as well as stances among them.
Joint Communication and Sensing in RIS-enabled mmWave Networks
Empowering cellular networks with augmented sensing capabilities is one of the key research areas in 6G communication systems.
A Fast Algorithm for Onboard Atmospheric Powered Descent Guidance
Atmospheric powered descent guidance can be solved by successive convexification; however, its onboard application is impeded by the sharp increase in computation caused by nonlinear aerodynamic forces.
Extensive Study of Multiple Deep Neural Networks for Complex Random Telegraph Signals
Time-fluctuating signals are ubiquitous and diverse in many physical, chemical, and biological systems, among which random telegraph signals (RTSs) refer to a series of instantaneous switching events between two discrete levels from single-particle movements.
Few-shot Reranking for Multi-hop QA via Language Model Prompting
To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking.
POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection
Ideology is at the core of political science research.
Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs
NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning.
Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Model
We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Efficient Argument Structure Extraction with Transfer Learning and Active Learning
Combined with transfer learning, substantial F1 score boost (5-25) can be further achieved during the early iterations of active learning across domains.
HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization
In this work, we present HIBRIDS, which injects Hierarchical Biases foR Incorporating Document Structure into the calculation of attention scores.
Anchor Graph Structure Fusion Hashing for Cross-Modal Similarity Search
Cross-modal hashing still has some challenges needed to address: (1) most existing CMH methods take graphs as input to model data distribution.
Auto robust relative radiometric normalization via latent change noise modelling
Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.
2020 CATARACTS Semantic Segmentation Challenge
In 2020, we released pixel-wise semantic annotations for anatomy and instruments for 4670 images sampled from 25 videos of the CATARACTS training set.
Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning
Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.
Explaining Point Processes by Learning Interpretable Temporal Logic Rules
We propose a principled method to learn a set of human-readable logic rules to explain temporal point processes.
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization
We study generating abstractive summaries that are faithful and factually consistent with the given articles.
Controllable Summarization with Constrained Markov Decision Process
We study controllable text summarization which allows users to gain control on a particular attribute (e. g., length limit) of the generated summaries.
Controllable Open-ended Question Generation with A New Question Type Ontology
We first define a new question type ontology which differentiates the nuanced nature of questions better than widely used question words.
Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
In this paper, we model the propagation of the COVID-19 as spatio-temporal point processes and propose a generative and intensity-free model to track the spread of the disease.
An Efficient Group-based Search Engine Marketing System for E-Commerce
With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies.
Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment
We address the problem of unsupervised localization of key-steps and feature learning in instructional videos using both visual and language instructions.
LoRA: Low-Rank Adaptation of Large Language Models
We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.
DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation
To enrich the generation with diverse content, we further propose to use large pre-trained models to predict relevant concepts and to generate claims.
TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level.
Unsupervised Learning of Multi-level Structures for Anomaly Detection
This paper first introduces a novel method to generate anomalous data by breaking up global structures while preserving local structures of normal data at multiple levels.
Attention Head Masking for Inference Time Content Selection in Abstractive Summarization
Using attention head masking, we are able to reveal the relation between encoder-decoder attentions and content selection behaviors of summarization models.
Efficient Attentions for Long Document Summarization
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization.
Inference Time Style Control for Summarization
How to generate summaries of different styles without requiring corpora in the target styles, or training separate models?
MD-MTL: An Ensemble Med-Multi-Task Learning Package for DiseaseScores Prediction and Multi-Level Risk Factor Analysis
In this paper, we developed a new ensemble machine learning Python package based on multi-task learning (MTL), referred to as the Med-Multi-Task Learning (MD-MTL) package and applied it in predicting disease scores of patients, and in carrying out risk factor analysis on multiple subgroups of patients simultaneously.
Annotation-Efficient Learning for Medical Image Segmentation based on Noisy Pseudo Labels and Adversarial Learning
In this paper, we propose an annotation-efficient learning framework for segmentation tasks that avoids annotations of training images, where we use an improved Cycle-Consistent Generative Adversarial Network (GAN) to learn from a set of unpaired medical images and auxiliary masks obtained either from a shape model or public datasets.
Adaptive Federated Learning and Digital Twin for Industrial Internet of Things
Industrial Internet of Things (IoT) enables distributed intelligent services varying with the dynamic and realtime industrial devices to achieve Industry 4. 0 benefits.
PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation
In this work, we present a novel content-controlled text generation framework, PAIR, with planning and iterative refinement, which is built upon a large model, BART.
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event
Understanding discourse structures of news articles is vital to effectively contextualize the occurrence of a news event.
Ranked #5 on
Text Classification
on NewsDiscourse
Dynamic Online Conversation Recommendation
Trending topics in social media content evolve over time, and it is therefore crucial to understand social media users and their interpersonal communications in a dynamic manner.
Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM
Fall event detection, as one of the greatest risks to the elderly, has been a hot research issue in the solitary scene in recent years.
XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference
We therefore propose a novel model, XREF, that leverages attention mechanisms to (1) pinpoint relevant context within comments, and (2) detect supporting entities from the news article.
Provably Robust Metric Learning
Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied.
Reducing the X-ray radiation exposure frequency in cardio-angiography via deep-learning based video interpolation
With the help of this technology, doctors can significantly reduce exposure frequency and intensity of the X-ray during coronary angiography.
Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data
By constraining adversarial perturbations in a low-dimensional subspace via spanning an auxiliary unlabeled dataset, the spanning attack significantly improves the query efficiency of a wide variety of existing black-box attacks.
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward
Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive.
Coronary Artery Segmentation in Angiographic Videos Using A 3D-2D CE-Net
This article proposes a new video segmentation framework that can extract the clearest and most comprehensive coronary angiography images from a video sequence, thereby helping physicians to better observe the condition of blood vessels.
Weakly-supervised 3D coronary artery reconstruction from two-view angiographic images
The reconstruction of three-dimensional models of coronary arteries is of great significance for the localization, evaluation and diagnosis of stenosis and plaque in the arteries, as well as for the assisted navigation of interventional surgery.
Robust Medical Instrument Segmentation Challenge 2019
The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data.
Asymmetric Correlation Quantization Hashing for Cross-modal Retrieval
Due to the superiority in similarity computation and database storage for large-scale multiple modalities data, cross-modal hashing methods have attracted extensive attention in similarity retrieval across the heterogeneous modalities.
Cluster-wise Unsupervised Hashing for Cross-Modal Similarity Search
Large-scale cross-modal hashing similarity retrieval has attracted more and more attention in modern search applications such as search engines and autopilot, showing great superiority in computation and storage.
Neural Conversation Recommendation with Online Interaction Modeling
The prevalent use of social media leads to a vast amount of online conversations being produced on a daily basis.
Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior Policies
We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies.
Learning Robust Representations with Graph Denoising Policy Network
Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.
In Plain Sight: Media Bias Through the Lens of Factual Reporting
The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection.
An Entity-Driven Framework for Abstractive Summarization
Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.
Sentence-Level Content Planning and Style Specification for Neural Text Generation
Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems.
Tackling Ordinal Regression Problem for Heterogeneous Data: Sparse and Deep Multi-Task Learning Approaches
Many real-world datasets are labeled with natural orders, i. e., ordinal labels.
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure.
Evaluating the Robustness of Nearest Neighbor Classifiers: A Primal-Dual Perspective
Furthermore, we show that dual solutions for these QP problems could give us a valid lower bound of the adversarial perturbation that can be used for formal robustness verification, giving us a nice view of attack/verification for NN models.
Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards
To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases.
Argument Generation with Retrieval, Planning, and Realization
Automatic argument generation is an appealing but challenging task.
Joint Effects of Context and User History for Predicting Online Conversation Re-entries
We hypothesize that both the context of the ongoing conversations and the users' previous chatting history will affect their continued interests in future engagement.
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.
Optimal margin Distribution Network
Recent research about margin theory has proved that maximizing the minimum margin like support vector machines does not necessarily lead to better performance, and instead, it is crucial to optimize the margin distribution.
Argument Mining for Understanding Peer Reviews
Peer-review plays a critical role in the scientific writing and publication ecosystem.
IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules
Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements.
Improving Generalization of Deep Neural Networks by Leveraging Margin Distribution
We utilize a convex margin distribution loss function on the deep neural networks to validate our theoretical results by optimizing the margin ratio.
Learning Segmentation Masks with the Independence Prior
We get appealing results in both tasks, which shows the independence prior is useful for instance segmentation and it is possible to unsupervisedly learn instance masks with only one image.
Hull Form Optimization with Principal Component Analysis and Deep Neural Network
Designing and modifying complex hull forms for optimal vessel performances have been a major challenge for naval architects.
Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information
Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization.
GraphSeq2Seq: Graph-Sequence-to-Sequence for Neural Machine Translation
In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.
Semi-Supervised Learning for Neural Keyphrase Generation
We study the problem of generating keyphrases that summarize the key points for a given document.
One vs. Many QA Matching with both Word-level and Sentence-level Attention Network
Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community.
Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation
Prior relevant studies recommend treatments either use supervised learning (e. g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e. g. maximizing evaluation signal which indicates cumulative reward from survival rates).
Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse
We propose a statistical model that jointly captures: (1) topics for representing user interests and conversation content, and (2) discourse modes for describing user replying behavior and conversation dynamics.
Neural Argument Generation Augmented with Externally Retrieved Evidence
High quality arguments are essential elements for human reasoning and decision-making processes.
A Pilot Study of Domain Adaptation Effect for Neural Abstractive Summarization
We study the problem of domain adaptation for neural abstractive summarization.
Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes
Using a dataset of 118 Oxford-style debates, our model's combination of content (as latent topics) and style (as linguistic features) allows us to predict audience-adjudicated winners with 74% accuracy, significantly outperforming linguistic features alone (66%).
Joint Modeling of Content and Discourse Relations in Dialogues
We present a joint modeling approach to identify salient discussion points in spoken meetings as well as to label the discourse relations between speaker turns.
Understanding and Detecting Supporting Arguments of Diverse Types
We investigate the problem of sentence-level supporting argument detection from relevant documents for user-specified claims.
Summarizing Decisions in Spoken Meetings
This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision.
Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems
Our session-based models outperform the state-of-the-art method for entity extraction task in SDS.
Focused Meeting Summarization via Unsupervised Relation Extraction
We present a novel unsupervised framework for focused meeting summarization that views the problem as an instance of relation extraction.
A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization.
Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings
We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify "summary-worthy" words.
Improving Agreement and Disagreement Identification in Online Discussions with A Socially-Tuned Sentiment Lexicon
For example, the isotonic CRF model achieves F1 scores of 0. 74 and 0. 67 for agreement and disagreement detection, when a linear chain CRF obtains 0. 58 and 0. 56 for the discussions on Wikipedia Talk pages.
A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection
We investigate the novel task of online dispute detection and propose a sentiment analysis solution to the problem: we aim to identify the sequence of sentence-level sentiments expressed during a discussion and to use them as features in a classifier that predicts the DISPUTE/NON-DISPUTE label for the discussion as a whole.
Query-Focused Opinion Summarization for User-Generated Content
We present a submodular function-based framework for query-focused opinion summarization.
Socially-Informed Timeline Generation for Complex Events
Existing timeline generation systems for complex events consider only information from traditional media, ignoring the rich social context provided by user-generated content that reveals representative public interests or insightful opinions.
Neural Network-Based Abstract Generation for Opinions and Arguments
We study the problem of generating abstractive summaries for opinionated text.
