Search Results for author:
Found 40 papers, 5 papers with code
Compositional Generalization in Spoken Language Understanding
State-of-the-art spoken language understanding (SLU) models have shown tremendous success in benchmark SLU datasets, yet they still fail in many practical scenario due to the lack of model compositionality when trained on limited training data.
Token Fusion: Bridging the Gap between Token Pruning and Token Merging
In this paper, we introduce "Token Fusion" (ToFu), a method that amalgamates the benefits of both token pruning and token merging.
Prompt Tuning for Zero-shot Compositional Learning
In order to achieve this goal, a model has to be "smart" and "knowledgeable".
Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters
We show that STAMINA outperforms the prior SOTA for the setting of text-to-image continual customization on a 50-concept benchmark composed of landmarks and human faces, with no stored replay data.
Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA
We show that C-LoRA not only outperforms several baselines for our proposed setting of text-to-image continual customization, which we refer to as Continual Diffusion, but that we achieve a new state-of-the-art in the well-established rehearsal-free continual learning setting for image classification.
To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement
We show that existing deep keyword spotting mechanisms can be improved by Successive Refinement, where the system first classifies whether the input audio is speech or not, followed by whether the input is keyword-like or not, and finally classifies which keyword was uttered.
ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation
Such object navigation tasks usually require large-scale training in visual environments with labeled objects, which generalizes poorly to novel objects in unknown environments.
GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer
We first develop a graph-based ranking for measuring the importance of attention heads, and the extracted importance information is further integrated to an optimization-based procedure to impose the heterogeneous structured sparsity patterns on the ViT models.
Numerical Optimizations for Weighted Low-rank Estimation on Language Model
However, standard SVD treats the parameters within the matrix with equal importance, which is a simple but unrealistic assumption.
Language model compression with weighted low-rank factorization
In other words, the optimization objective of SVD is not aligned with the trained model's task accuracy.
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients
Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another.
MGA-VQA: Multi-Granularity Alignment for Visual Question Answering
In contrast to previous works, our model splits alignment into different levels to achieve learning better correlations without needing additional data and annotations.
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding
Most existing continual learning approaches suffer from low accuracy and performance fluctuation, especially when the distributions of old and new data are significantly different.
Lite-MDETR: A Lightweight Multi-Modal Detector
The key primitive is that Dictionary-Lookup-Transformormations (DLT) is proposed to replace Linear Transformation (LT) in multi-modal detectors where each weight in Linear Transformation (LT) is approximately factorized into a smaller dictionary, index, and coefficient.
Automatic Mixed-Precision Quantization Search of BERT
Knowledge distillation, Weight pruning, and Quantization are known to be the main directions in model compression.
Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data
We are the first to propose a method that works well across both OOD detection and calibration and under different types of shifts.
DictFormer: Tiny Transformer with Shared Dictionary
DictFormer significantly reduces the redundancy in the transformer's parameters by replacing the prior transformer's parameters with compact, shared dictionary, a few unshared coefficients, and indices.
Exploring Covariate and Concept Shift for Detection and Confidence Calibration of Out-of-Distribution Data
To this end, we theoretically derive two score functions for OOD detection, the covariate shift score and concept shift score, based on the decomposition of KL-divergence for both scores, and propose a geometrically-inspired method (Geometric ODIN) to improve OOD detection under both shifts with only in-distribution data.
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU
This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning
Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time.
Ranked #5 on
Class Incremental Learning
on cifar100
An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction
In this paper, we introduce a novel multi-step spoken language understanding system based on adversarial learning that can leverage the multiround user's feedback to update slot values.
SAFENet: A Secure, Accurate and Fast Neural Network Inference
A cryptographic neural network inference service is an efficient way to allow two parties to execute neural network inference without revealing either party’s data or model.
Modeling Token-level Uncertainty to Learn Unknown Concepts in SLU via Calibrated Dirichlet Prior RNN
We design a Dirichlet Prior RNN to model high-order uncertainty by degenerating as softmax layer for RNN model training.
Generating Dialogue Responses from a Semantic Latent Space
Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary.
Reward Constrained Interactive Recommendation with Natural Language Feedback
Text-based interactive recommendation provides richer user feedback and has demonstrated advantages over traditional interactive recommender systems.
PGLP: Customizable and Rigorous Location Privacy through Policy Graph
Third, we design a private location trace release framework that pipelines the detection of location exposure, policy graph repair, and private trajectory release with customizable and rigorous location privacy.
Cryptography and Security Computers and Society
Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning
Text-based interactive recommendation provides richer user preferences and has demonstrated advantages over traditional interactive recommender systems.
A Progressive Model to Enable Continual Learning for Semantic Slot Filling
ProgModel consists of a novel context gate that transfers previously learned knowledge to a small size expanded component; and meanwhile enables this new component to be fast trained to learn from new data.
Fast Domain Adaptation of Semantic Parsers via Paraphrase Attention
However, state-of-the art attention based neural parsers are slow to retrain which inhibits real time domain adaptation.
Iterative Delexicalization for Improved Spoken Language Understanding
Recurrent neural network (RNN) based joint intent classification and slot tagging models have achieved tremendous success in recent years for building spoken language understanding and dialog systems.
SkillBot: Towards Automatic Skill Development via User Demonstration
We present SkillBot that takes the first step to enable end users to teach new skills in personal assistants (PA).
How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection
Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs.
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded
Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image.
A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
The most effective algorithms are based on the structures of sequence to sequence models (or "encoder-decoder" models), and generate the intents and semantic tags either using separate models or a joint model.
Ranked #1 on
Intent Detection
on ATIS
A Variational Dirichlet Framework for Out-of-Distribution Detection
With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications.
User Information Augmented Semantic Frame Parsing using Coarse-to-Fine Neural Networks
The results show that our approach leverages such simple user information to outperform state-of-the-art approaches by 0. 25% for intent detection and 0. 31% for slot filling using standard training data.
Robust Spoken Language Understanding via Paraphrasing
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems.
CRUISE: Cold-Start New Skill Development via Iterative Utterance Generation
We present a system, CRUISE, that guides ordinary software developers to build a high quality natural language understanding (NLU) engine from scratch.
Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning
The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal states.
