Search Results for author:
Found 388 papers, 153 papers with code
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization.
Improving Domain Adaptation through Extended-Text Reading Comprehension
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
ResLoRA: Identity Residual Mapping in Low-Rank Adaption
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs).
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.
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.
BARS-CTR: Open Benchmarking for Click-Through Rate Prediction
We have publicly released the benchmarking code, evaluation protocols, and hyper-parameter settings of our work to promote reproducible research in this field.
Sogou Machine Reading Comprehension Toolkit
In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting.
Simplify the Usage of Lexicon in Chinese NER
This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information.
Ranked #8 on
Chinese Named Entity Recognition
on Resume NER
Chinese Named Entity Recognition
named-entity-recognition
+2
Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study
While neural network-based models have achieved impressive performance on a large body of NLP tasks, the generalization behavior of different models remains poorly understood: Does this excellent performance imply a perfect generalization model, or are there still some limitations?
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Large language models have unlocked strong multi-task capabilities from reading instructive prompts.
Ranked #2 on
Zero-shot Named Entity Recognition (NER)
on CrossNER
(using extra training data)
PromptBERT: Improving BERT Sentence Embeddings with Prompts
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
Multivariate Time-series Anomaly Detection via Graph Attention Network
Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications.
BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
To further employ the power of quantization, the mixed precision technique is incorporated in our framework by approximating the inter-layer and intra-layer sensitivity.
Deblur-NeRF: Neural Radiance Fields from Blurry Images
We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.
EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs.
FENeRF: Face Editing in Neural Radiance Fields
2D GANs can generate high fidelity portraits but with low view consistency.
GS-IR: 3D Gaussian Splatting for Inverse Rendering
We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results.
AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?
With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets.
RethinkCWS: Is Chinese Word Segmentation a Solved Task?
The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models.
A Partition Filter Network for Joint Entity and Relation Extraction
In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition.
Ranked #1 on
Relation Extraction
on ADE Corpus
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries.
UNBERT: User-News Matching BERT for News Recommendation
Nowadays, news recommendation has become a popular channel for users to access news of their interests.
A Neural Corpus Indexer for Document Retrieval
To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
Template-free Prompt Tuning for Few-shot NER
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words.
Orthogonal Subspace Learning for Language Model Continual Learning
In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks.
Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training
Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components.
Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling
In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.
Time-Series Anomaly Detection Service at Microsoft
At Microsoft, we develop a time-series anomaly detection service which helps customers to monitor the time-series continuously and alert for potential incidents on time.
One2Set: Generating Diverse Keyphrases as a Set
In this work, we propose a new training paradigm One2Set without predefining an order to concatenate the keyphrases.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
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
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length.
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.
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
Furthermore, a sole emphasis on outcomes disregards the intricate capabilities essential for LLMs to effectively utilize tools.
CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending
In fact, anomalous behaviors harming long context extrapolation exist between Rotary Position Embedding (RoPE) and vanilla self-attention unveiled by our work.
How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders
Masked Autoencoders (MAE) based on a reconstruction task have risen to be a promising paradigm for self-supervised learning (SSL) and achieve state-of-the-art performance across different benchmark datasets.
Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control
Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis
Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on resource-limited devices.
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
In this paper, we introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
The advancement of large language models (LLMs) has significantly propelled the field of code generation.
Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders
Automatic chat summarization can help people quickly grasp important information from numerous chat messages.
Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation.
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
NER model has achieved promising performance on standard NER benchmarks.
Ranked #8 on
Named Entity Recognition (NER)
on WNUT 2017
Movie101: A New Movie Understanding Benchmark
Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking.
ReCO: A Large Scale Chinese Reading Comprehension Dataset on Opinion
The release of ReCO consists of 300k questions that to our knowledge is the largest in Chinese reading comprehension.
SENT: Sentence-level Distant Relation Extraction via Negative Training
In this work, we propose the use of negative training (NT), in which a model is trained using complementary labels regarding that ``the instance does not belong to these complementary labels".
Long Short-Term Memory with Dynamic Skip Connections
In recent years, long short-term memory (LSTM) has been successfully used to model sequential data of variable length.
Ranked #33 on
Sentiment Analysis
on IMDb
HousE: Knowledge Graph Embedding with Householder Parameterization
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties.
Democratizing Reasoning Ability: Tailored Learning from Large Language Model
In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability.
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution
Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models.
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Our theory suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and the overlapped augmented views (i. e., the chaos) create a ladder for contrastive learning to gradually learn class-separated representations.
Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes
We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales.
Image super-resolution via dynamic network
In this paper, we present a dynamic network for image super-resolution (DSRNet), which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block.
Ranked #49 on
Image Super-Resolution
on Set14 - 4x upscaling
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
Succinct and Robust Multi-Agent Communication With Temporal Message Control
Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL).
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
Uncertainty-Aware Label Refinement for Sequence Labeling
Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks.
An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models
The Cross-Market Recommendation task of WSDM CUP 2022 is about finding solutions to improve individual recommendation systems in resource-scarce target markets by leveraging data from similar high-resource source markets.
Non-negative Contrastive Learning
In this paper, we propose Non-negative Contrastive Learning (NCL), a renaissance of Non-negative Matrix Factorization (NMF) aimed at deriving interpretable features.
PathQG: Neural Question Generation from Facts
Human evaluation also proves that our model is able to generate relevant and informative questions.
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks.
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs).
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response.
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales.
On the Generalization of Multi-modal Contrastive Learning
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs.
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
A Relation-Oriented Clustering Method for Open Relation Extraction
The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE).
Ranked #1 on
Relation Extraction
on FewRel
Model-enhanced Vector Index
We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.
Person Re-identification in Aerial Imagery
Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.
Heterogeneous Graph Neural Networks for Keyphrase Generation
The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not.
Why Do We Click: Visual Impression-aware News Recommendation
In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation.
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction
However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems.
Ranked #1 on
Entity Linking
on FUNSD
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training.
Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning
In response to this problem, we propose a new fine-grained evaluation metric to improve the RL framework, which considers different granularities: token-level $F_1$ score, edit distance, duplication, and prediction quantities.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector
Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media.
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences.
Math Word Problem Solving with Explicit Numerical Values
In recent years, math word problem solving has received considerable attention and achieved promising results, but previous methods rarely take numerical values into consideration.
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics.
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning.
A Comparative Measurement Study of Deep Learning as a Service Framework
Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices.
Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining
With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization.
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task.
An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving
Specifically, an edge-enhanced hierarchical graph encoder is used to incorporate edge label information.
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
Unifying Event Detection and Captioning as Sequence Generation via Pre-Training
Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning.
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks.
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs).
Discrete Argument Representation Learning for Interactive Argument Pair Identification
In this paper, we focus on extracting interactive argument pairs from two posts with opposite stances to a certain topic.
Improving Non-autoregressive Generation with Mixup Training
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.
Towards Understanding Omission in Dialogue Summarization
By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization.
Incorporating Argument-Level Interactions for Persuasion Comments Evaluation using Co-attention Model
In this paper, we investigate the issue of persuasiveness evaluation for argumentative comments.
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Each score is derived from machine perceptual differences between original and compressed images.
IRGen: Generative Modeling for Image Retrieval
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored.
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model
Pretrained language models have achieved remarkable success in various natural language processing tasks.
Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Executing actions in a correlated manner is a common strategy for human coordination that often leads to better cooperation, which is also potentially beneficial for cooperative multi-agent reinforcement learning (MARL).
RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification
Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars.
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models.
Towards Better Entity Linking with Multi-View Enhanced Distillation
Aiming at learning entity representations that can match divergent mentions, this paper proposes a Multi-View Enhanced Distillation (MVD) framework, which can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders.
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
Adversarial training is one of the best-performing methods in improving the robustness of deep language models.
Learning Task-specific Representation for Novel Words in Sequence Labeling
However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance.
AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search
Our motivation lies in incorporating the tremendous amount of unsupervised user behavior data from the historical search logs as the complementary graph to facilitate relevance modeling.
Iterative GNN-based Decoder for Question Generation
However, (1) they ignore the rich structure information that is hidden in the previously generated text.
Multi-view Information Bottleneck Without Variational Approximation
By "intelligently" fusing the complementary information across different views, multi-view learning is able to improve the performance of classification tasks.
On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe
Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference.
Enhancing Event-Level Sentiment Analysis with Structured Arguments
Previous studies about event-level sentiment analysis (SA) usually model the event as a topic, a category or target terms, while the structured arguments (e. g., subject, object, time and location) that have potential effects on the sentiment are not well studied.
Searching for Optimal Subword Tokenization in Cross-domain NER
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages.
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
However, general matching methods lack explicit modeling of the above matching pattern.
Open Set Relation Extraction via Unknown-Aware Training
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Identification and analysis of symmetrical patterns in the natural world have led to significant discoveries across various scientific fields, such as the formulation of gravitational laws in physics and advancements in the study of chemical structures.
Data-driven decision-focused surrogate modeling
We introduce the concept of decision-focused surrogate modeling for solving computationally challenging nonlinear optimization problems in real-time settings.
Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation
The results show the competitiveness of our proposed framework and evaluator in counter-argument generation tasks.
Length Generalization of Causal Transformers without Position Encoding
Generalizing to longer sentences is important for recent Transformer-based language models.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
A Progressive Framework for Role-Aware Rumor Resolution
Existing works on rumor resolution have shown great potential in recognizing word appearance and user participation.
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks
Specifically, we re-formulate both token and sentence classification tasks into a unified language modeling task, and map label spaces of different tasks into the same vocabulary space.
A Structure-Aware Argument Encoder for Literature Discourse Analysis
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
Efficient Adversarial Training with Robust Early-Bird Tickets
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs).
Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?
We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.
Universal Multi-modal Entity Alignment via Iteratively Fusing Modality Similarity Paths
The objective of Entity Alignment (EA) is to identify equivalent entity pairs from multiple Knowledge Graphs (KGs) and create a more comprehensive and unified KG.
Graph Signal Diffusion Model for Collaborative Filtering
In this paper, we make novel adaptions of diffusion model and propose Graph Signal Diffusion Model for Collaborative Filtering (named GiffCF).
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios.
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
The generated demos strategically interpolate between existing demos and the given query, transforming the query from OOD to ID.
Image Super-Resolution Using a Wavelet-based Generative Adversarial Network
Existing work like Super-Resolution Using a Generative Adversarial Network (SRGAN) can effectively restore the texture details of the image.
Decomposition and Adaptive Sampling for Data-Driven Inverse Linear Optimization
This work addresses inverse linear optimization where the goal is to infer the unknown cost vector of a linear program.
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization
We then propose a meta-learning-based method to learn to align conceptual spaces of different languages, which facilitates zero-shot and few-shot generalization in concept classification and also offers insights into the cross-lingual in-context learning phenomenon.
Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining
In this paper, we propose the Hierarchical Argumentation Graph (Hi-ArG), a new structure to organize arguments.
Minimizing Maximum Regret in Commitment Constrained Sequential Decision Making
In cooperative multiagent planning, it can often be beneficial for an agent to make commitments about aspects of its behavior to others, allowing them in turn to plan their own behaviors without taking the agent's detailed behavior into account.
Learning Word Embeddings from Intrinsic and Extrinsic Views
To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries, Wiki link prediction, and document classification.
Optimality of Graphlet Screening in High Dimensional Variable Selection
Compared to m-variate brute-forth screening that has a computational cost of p^m, the GS only has a computational cost of p (up to some multi-log(p) factors) in screening.
Multiscale probability transformation of basic probability assignment
In this paper, multiscale probability transformation of basic probability assignment based on the belief function and the plausibility function is proposed, which is a generalization of the pignistic probability transformation.
Distance function of D numbers
A distance function of D numbers is proposed to measure the distance between two D numbers.
A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras
Based on the MPC model and projective transformation, we propose a calibration algorithm to verify our light field camera model.
Predicting protein inter-residue contacts using composite likelihood maximization and deep learning
We further present successful application of the predicted contacts to accurately build tertiary structures for proteins in the PSICOV dataset.
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging
However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles.
Ranked #2 on
Part-Of-Speech Tagging
on Ritter
Cross-Domain Sentiment Classification with Target Domain Specific Information
And we introduce a few target domain labeled data for learning domain-specific information.
Large-scale Opinion Relation Extraction with Distantly Supervised Neural Network
We investigate the task of open domain opinion relation extraction.
Part-of-Speech Tagging for Twitter with Adversarial Neural Networks
In this work, we study the problem of part-of-speech tagging for Tweets.
Ranked #3 on
Part-Of-Speech Tagging
on Ritter
A Lexicon-Based Supervised Attention Model for Neural Sentiment Analysis
Attention mechanisms have been leveraged for sentiment classification tasks because not all words have the same importance.
Hashtag Recommendation Using End-To-End Memory Networks with Hierarchical Attention
By incorporating the hierarchical attention mechanism, the relative improvement in the proposed method over the state-of-the-art method is around 67. 9{\%} in the F1-score.
A Learning Error Analysis for Structured Prediction with Approximate Inference
In this work, we try to understand the differences between exact and approximate inference algorithms in structured prediction.
Dynamic Feature Learning for Partial Face Recognition
Partial face recognition (PFR) in unconstrained environment is a very important task, especially in video surveillance, mobile devices, etc.
100+ Times Faster Weighted Median Filter (WMF)
Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation.
2D Semantic Segmentation task 1 (8 classes)
Optical Flow Estimation
+2
4D Light Field Superpixel and Segmentation
Superpixel segmentation of 2D image has been widely used in many computer vision tasks.
A Unified Framework for Marketing Budget Allocation
In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task.
Posterior-regularized REINFORCE for Instance Selection in Distant Supervision
This paper provides a new way to improve the efficiency of the REINFORCE training process.
Learning Fast Matching Models from Weak Annotations
The proposed training framework targets on mitigating both issues, by treating the stronger but undeployable models as annotators, and learning a deployable model from both human provided relevance labels and weakly annotated search log data.
Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction
In intra-frame compression of point cloud color attributes, results demonstrate that our method performs better than the state-of-the-art region-adaptive hierarchical transform (RAHT) system, and on average a 29. 37$\%$ BD-rate gain is achieved.
Multimedia
Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs
Crowd counting in single-view images has achieved outstanding performance on existing counting datasets.
Ray-Space Projection Model for Light Field Camera
A homogeneous ray-space projection matrix and a fundamental matrix are then proposed to establish ray-ray correspondences among multiple light fields.
Address Instance-level Label Prediction in Multiple Instance Learning
Existent approaches in this field were mainly designed for the bag-level label prediction (predict labels for bags) but not the instance-level (predict labels for instances), with the task loss being only defined at the bag level.
Seq-SetNet: Exploring Sequence Sets for Inferring Structures
Therefore, the traditional deep neural networks designed for image processing cannot be directly applied on sequence sets.
Multiple Sequence Alignment
Protein Secondary Structure Prediction
+1
Self-driving scale car trained by Deep reinforcement learning
To improve the generalization ability for the driving behavior, the reinforcement learning method requires extrinsic reward from the real environment, which may damage the car.
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework.
A Multi-Task Learning Framework for Extracting Bacteria Biotope Information
This paper presents a novel transfer multi-task learning method for Bacteria Biotope rel+ner task at BioNLP-OST 2019.
A Lexicon-Based Graph Neural Network for Chinese NER
Recurrent neural networks (RNN) used for Chinese named entity recognition (NER) that sequentially track character and word information have achieved great success.
Ranked #13 on
Chinese Named Entity Recognition
on OntoNotes 4
Chinese Named Entity Recognition
named-entity-recognition
+3
Asynchronous Deep Interaction Network for Natural Language Inference
However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora.
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically.
Ranked #9 on
Visual Storytelling
on VIST
A Machine Learning-enhanced Robust P-Phase Picker for Real-time Seismic Monitoring
To this end, in this paper, we present a machine learning-enhanced framework based on ensemble learning strategy, EL-Picker, for the automatic identification of seismic P-phase arrivals on continuous and massive waveforms.
3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels
Unlike MVMS, we propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D ground-plane ones.
Context-Aware Attention Network for Image-Text Retrieval
As a typical cross-modal problem, image-text bi-directional retrieval relies heavily on the joint embedding learning and similarity measure for each image-text pair.
Single-Frame based Deep View Synchronization for Unsynchronized Multi-Camera Surveillance
To handle the issue of unsynchronized multi-cameras, in this paper, we propose a synchronization model that works in conjunction with existing DNN-based multi-view models, thus avoiding the redesign of the whole model.
Bitcoin Transaction Forecasting with Deep Network Representation Learning
First, we explore three interesting properties between Bitcoin transaction accounts: topological connectivity pattern of Bitcoin accounts, transaction amount pattern, and transaction dynamics.
Variational Bayesian Line Spectral Estimation with Multiple Measurement Vectors
In this paper, the line spectral estimation (LSE) problem with multiple measurement vectors (MMVs) is studied utilizing the Bayesian methods.
Information Theory Information Theory
Grid-less Variational Direction of Arrival Estimation in Heteroscedastic Noise Environment
This paper studies DOA in heteroscedastic noise (HN) environment, where the variance of noise is varied across the snapshots and the antennas.
Vector Approximate Message Passing Algorithm for Structured Perturbed Sensing Matrix
In this paper, we consider a general form of noisy compressive sensing (CS) where the sensing matrix is not precisely known.
Signal Processing
Two Step Joint Model for Drug Drug Interaction Extraction
When patients need to take medicine, particularly taking more than one kind of drug simultaneously, they should be alarmed that there possibly exists drug-drug interaction.
Drug–drug Interaction Extraction
named-entity-recognition
+4
