Search Results for author:
Found 77 papers, 28 papers with code
Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition
In this paper, we decompose the sentence into two parts: entity and context, and rethink the relationship between them and model performance from a causal perspective.
Meta Distant Transfer Learning for Pre-trained Language Models
For tasks related to distant domains with different class label sets, PLMs may memorize non-transferable knowledge for the target domain and suffer from negative transfer.
Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug Fixing
Obviously, unchanged fix is not the correct fix because it is the same as the buggy code that needs to be fixed.
Continual Few-shot Intent Detection
Intent detection is at the core of task-oriented dialogue systems.
UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings
Inspired by the fact that words with similar semantic can share a part of weights, we divide the embeddings of words into two parts: unique embedding and class embedding.
SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC
SMAC-HARD supports customizable opponent strategies, randomization of adversarial policies, and interfaces for MARL self-play, enabling agents to generalize to varying opponent behaviors and improve model stability.
VCBench: A Controllable Benchmark for Symbolic and Abstract Challenges in Video Cognition
Recent advancements in Large Video-Language Models (LVLMs) have driven the development of benchmarks designed to assess cognitive abilities in video-based tasks.
MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation
In our experiments, we demonstrate that MBA-SLAM surpasses previous state-of-the-art methods in both camera localization and map reconstruction, showcasing superior performance across a range of datasets, including synthetic and real datasets featuring sharp images as well as those affected by motion blur, highlighting the versatility and robustness of our approach.
A New Approach to Solving SMAC Task: Generating Decision Tree Code from Large Language Models
StarCraft Multi-Agent Challenge (SMAC) is one of the most commonly used experimental environments in multi-agent reinforcement learning (MARL), where the specific task is to control a set number of allied units to defeat enemy forces.
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
With tree search and evaluation models, it can efficiently guide each instruction to evolve into a high-quality form, aiding in instruction fine-tuning.
PowerPM: Foundation Model for Power Systems
PowerPM consists of a temporal encoder and a hierarchical encoder.
Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency
Specifically, SliSum divides the source article into overlapping windows, and utilizes LLM to generate local summaries for the content in the windows.
PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Recent advancements in Large Multimodal Models (LMMs) have leveraged extensive multimodal datasets to enhance capabilities in complex knowledge-driven tasks.
Physical formula enhanced multi-task learning for pharmacokinetics prediction
Overall, our work illustrates the benefits and potential of using PEMAL in AIDD and other scenarios with data scarcity and noise.
Domain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network
A new benchmark for cross-domain MAV detection is proposed based on the proposed dataset.
Effective Two-Stage Knowledge Transfer for Multi-Entity Cross-Domain Recommendation
In the end, the extracted common knowledge is adopted for target entity model training.
TeleChat Technical Report
Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe.
Global-Local MAV Detection under Challenging Conditions based on Appearance and Motion
In this paper, we propose a global-local MAV detector that can fuse both motion and appearance features for MAV detection under challenging conditions.
Mixed Distillation Helps Smaller Language Model Better Reasoning
While large language models (LLMs) have demonstrated exceptional performance in recent natural language processing (NLP) tasks, their deployment poses substantial challenges due to high computational and memory demands in real-world applications.
Why "classic" Transformers are shallow and how to make them go deep
Since its introduction in 2017, Transformer has emerged as the leading neural network architecture, catalyzing revolutionary advancements in many AI disciplines.
HierarchicalContrast: A Coarse-to-Fine Contrastive Learning Framework for Cross-Domain Zero-Shot Slot Filling
To alleviate this issue, we present a novel Hierarchical Contrastive Learning Framework (HiCL) for zero-shot slot filling.
Large Language Models Are Also Good Prototypical Commonsense Reasoners
Commonsense reasoning is a pivotal skill for large language models, yet it presents persistent challenges in specific tasks requiring this competence.
SAR ATR Method with Limited Training Data via an Embedded Feature Augmenter and Dynamic Hierarchical-Feature Refiner
The designed augmenter increases the amount of information available for supervised training and improves the separability of the extracted features.
SAR Ship Target Recognition Via Multi-Scale Feature Attention and Adaptive-Weighed Classifier
Therefore, we proposed a SAR ship recognition method via multi-scale feature attention and adaptive-weighted classifier to enhance features in each scale, and adaptively choose the effective feature scale for accurate recognition.
SAR Ship Target Recognition via Selective Feature Discrimination and Multifeature Center Classifier
However, the characteristics of SAR ship images, large inner-class variance, and small interclass difference lead to the whole features containing useless partial features and a single feature center for each class in the classifier failing with large inner-class variance.
An Entropy-Awareness Meta-Learning Method for SAR Open-Set ATR
In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes.
Crucial Feature Capture and Discrimination for Limited Training Data SAR ATR
Based on the initial recognition results, the feature capture module automatically searches and locks the crucial image regions for correct recognition, which we named as the golden key of image.
Causal SAR ATR with Limited Data via Dual Invariance
As a result, it has a detrimental causal effect damaging the efficacy of feature $X$ extracted from SAR images, leading to weak generalization of SAR ATR with limited data.
Global in Local: A Convolutional Transformer for SAR ATR FSL
Convolutional neural networks (CNNs) have dominated the synthetic aperture radar (SAR) automatic target recognition (ATR) for years.
SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network
The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated.
SAR ATR under Limited Training Data Via MobileNetV3
In recent years, deep learning has been widely used to solve the bottleneck problem of synthetic aperture radar (SAR) automatic target recognition (ATR).
Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering
Instead, in this paper, we find that instruction-tuning language models like Claude and ChatGPT can understand layout by spaces and line breaks.
Ranked #9 on
Visual Question Answering (VQA)
on DocVQA test
WYWEB: A NLP Evaluation Benchmark For Classical Chinese
To fully evaluate the overall performance of different NLP models in a given domain, many evaluation benchmarks are proposed, such as GLUE, SuperGLUE and CLUE.
Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering
Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases.
AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference
To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher single-student distillation framework, which allows distilling knowledge from multiple teachers to a single student.
Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
In this paper, we propose the Parameter Allocation & Regularization (PAR), which adaptively select an appropriate strategy for each task from parameter allocation and regularization based on its learning difficulty.
OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification
However, such models can't predict a relatively complete and variable-length label subset for each document, because they select positive labels relevant to the document by a fixed threshold or take top k labels in descending order of scores.
Multi Label Text Classification
Multi-Label Text Classification
+1
Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)
In this work, we aim to improve tail item recommendations while maintaining the overall performance with less training and serving cost.
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding.
Ranked #2 on
Semantic entity labeling
on FUNSD
DAMO-NLP at NLPCC-2022 Task 2: Knowledge Enhanced Robust NER for Speech Entity Linking
Speech Entity Linking aims to recognize and disambiguate named entities in spoken languages.
ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding
At first, a document graph is proposed to model complex relationships among multi-grained multimodal elements, in which salient visual regions are detected by a cluster-based method.
LFGCF: Light Folksonomy Graph Collaborative Filtering for Tag-Aware Recommendation
Recently, many efforts have been devoted to improving Tag-aware recommendation systems (TRS) with Graph Convolutional Networks (GCN), which has become new state-of-the-art for the general recommendation.
DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning
We evaluate our approach on a variety of knowledge driven and language understanding tasks, including NER, relation extraction, CommonsenseQA, OpenBookQA and GLUE.
Rethinking the Value of Gazetteer in Chinese Named Entity Recognition
Gazetteer is widely used in Chinese named entity recognition (NER) to enhance span boundary detection and type classification.
POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices
In this work, we propose the first-ever Transformer model (POViT) to efficiently design and simulate semiconductor photonic devices with multiple objectives.
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.
Multi-Label Image Recognition
Weakly-Supervised Object Localization
Variability of Neural Networks and Han-Layer: A Variability-Inspired Model
We introduce a notion of variability to view such issues under the setting of a fixed number of parameters which is, in general, a dominant cost-factor.
Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning
Second, we construct the plugable multi-modal scene retriever to retrieve scenes represented with pairs of an image and its stylized caption, which are similar to the query image or caption in the large-scale factual data.
KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference
In order to better understand the reason behind model behaviors (i. e., making predictions), most recent works have exploited generative models to provide complementary explanations.
DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework
In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.
RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition
We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.
Ranked #9 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Image Recognition
Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations
Then the representation of each dialogue turn is aggregated by a hierarchical structure to form the passage information, which is utilized in the current turn of DST.
A Lightweight and Gradient-Stable Neural Layer
To enhance resource efficiency and model deployability of neural networks, we propose a neural-layer architecture based on Householder weighting and absolute-value activating, called Householder-absolute neural layer or simply Han-layer.
Multi-layer Perceptron Trainability Explained via Variability
Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability.
Popularity-Opportunity Bias in Collaborative Filtering
This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias.
The simpler the better: vanilla sgd revisited
The stochastic gradient descent (SGD) method, first proposed in 1950's, has been the foundation for deep-neural-network (DNN) training with numerous enhancements including adding a momentum or adaptively selecting learning rates, or using both strategies and more.
Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources
More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources.
A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation
It is also very encouraging that our framework further improves head items and overall performance on top of the gains on tail items.
Federated Unsupervised Representation Learning
FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces.
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge
We present a new benchmark dataset called PARADE for paraphrase identification that requires specialized domain knowledge.
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition
Knowledge of a disease includes information of various aspects of the disease, such as signs and symptoms, diagnosis and treatment.
Biomedical named entity recognition using BERT in the machine reading comprehension framework
Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method.
Joint Partial Optimal Transport for Open Set Domain Adaptation
However, in a general setting when the target domain contains classes that are never observed in the source domain, namely in Open Set Domain Adaptation (OSDA), existing DA methods failed to work because of the interference of the extra unknown classes.
Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems
More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer.
MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response.
Lifelong Learning with Searchable Extension Units
To solve those problems, in this paper, we propose a new lifelong learning framework named Searchable Extension Units (SEU) by introducing Neural Architecture Search into lifelong learning, which breaks down the need for a predefined original model and searches for specific extension units for different tasks, without compromising the performance of the model on different tasks.
"Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model
And the arbitrator decides whether to wait or to make a response to the user directly.
Consistency-Aware Recommendation for User-Generated ItemList Continuation
Complementary to methods that exploit specific content patterns (e. g., as in song-based playlists that rely on audio features), the proposed approach models the consistency of item lists based on human curation patterns, and so can be deployed across a wide range of varying item types (e. g., videos, images, books).
Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge
Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks.
Teacher-Student Framework Enhanced Multi-domain Dialogue Generation
Dialogue systems dealing with multi-domain tasks are highly required.
Big-Data Clustering: K-Means or K-Indicators?
The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some "feature spaces", as is in spectral clustering.
An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition
Motivation: In biomedical research, chemical is an important class of entities, and chemical named entity recognition (NER) is an important task in the field of biomedical information extraction.
Ranked #6 on
Named Entity Recognition (NER)
on BC4CHEMD
Fast Similarity Search via Optimal Sparse Lifting
Similarity search is a fundamental problem in computing science with various applications and has attracted significant research attention, especially in large-scale search with high dimensions.
Fairness-Aware Recommendation of Information Curators
This paper highlights our ongoing efforts to create effective information curator recommendation models that can be personalized for individual users, while maintaining important fairness properties.
An Alternating Direction Algorithm for Matrix Completion with Nonnegative Factors
By taking the advantages of both nonnegativity and low-rankness, one can generally obtain superior results than those of just using one of the two properties.
Information Theory Numerical Analysis Information Theory Numerical Analysis
