Search Results for author:
Found 64 papers, 20 papers with code
Continual Learning via Explicit Structure Learning
During structure learning, the model optimizes for the best structure for the current task.
Few-Shot Intent Classification by Gauging Entailment Relationship Between Utterance and Semantic Label
Compared with DNNC, our proposed method is more efficient in both training and serving since it is based upon the entailment between query utterance and labels instead of all the training examples.
Personalized Federated Instruction Tuning via Neural Architecture Search
Federated Instruction Tuning (FIT) has shown the ability to achieve collaborative model instruction tuning among massive data owners without sharing private data.
Parameter-Efficient Detoxification with Contrastive Decoding
DETOXIGEN is an ensemble of a pre-trained language model (generator) and a detoxifier.
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
Large Language Models (LLMs) have demonstrated a powerful ability for text generation.
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text
Moreover, a significant gap in the current landscape is the absence of a realistic benchmark for evaluating the effectiveness of grounding LLMs on heterogeneous knowledge sources (e. g., knowledge base and text).
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating training samples and training processes.
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Recently, large language models (LLMs), especially those that are pretrained on code, have demonstrated strong capabilities in generating programs from natural language inputs in a few-shot or even zero-shot manner.
Investigating Answerability of LLMs for Long-Form Question Answering
As we embark on a new era of LLMs, it becomes increasingly crucial to understand their capabilities, limitations, and differences.
XGen-7B Technical Report
Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context.
Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs
This paper aims to fill this gap by investigating different methods of combining retrieved passages with LLMs to enhance answer generation.
EqGAN: Feature Equalization Fusion for Few-shot Image Generation
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity.
Few-shot Unified Question Answering: Tuning Models or Prompts?
Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks.
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution
It comprises two central pillars: (1) We parse the question of varying complexity into an intermediate representation, named H-expression, which is composed of simple questions as the primitives and symbolic operations representing the relationships among them; (2) To execute the resulting H-expressions, we design a hybrid executor, which integrates the deterministic rules to translate the symbolic operations with a drop-in neural reader network to answer each decomposed simple question.
CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
In this study, we attempt to render the training of LLMs for program synthesis more efficient by unifying four key components: (1) model architectures, (2) learning methods, (3) infill sampling, and, (4) data distributions.
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Our results demonstrate the strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings.
CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning
Based on the concept of Continual Learning (CL), we prove that CyclicFL approximates existing centralized pre-training methods in terms of classification and prediction performance.
AugTriever: Unsupervised Dense Retrieval by Scalable Data Augmentation
Dense retrievers have made significant strides in text retrieval and open-domain question answering, even though most achievements were made possible only with large amounts of human supervision.
Best-$k$ Search Algorithm for Neural Text Generation
We first investigate the vanilla best-first search (BFS) algorithm and then propose the Best-$k$ Search algorithm.
Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database
Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB).
Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models
Pre-trained multilingual language models show significant performance gains for zero-shot cross-lingual model transfer on a wide range of natural language understanding (NLU) tasks.
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation
Finally, we fine-tune the model with limited data with true labels to fully adapt it to the target domain.
BigIssue: A Realistic Bug Localization Benchmark
As machine learning tools progress, the inevitable question arises: How can machine learning help us write better code?
Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control
Abstractive summarization systems leveraging pre-training language models have achieved superior results on benchmark datasets.
Modeling Multi-hop Question Answering as Single Sequence Prediction
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA.
OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval
When finetuned on a single rich-resource language pair, be it English-centered or not, our model is able to match the performance of the ones finetuned on all language pairs under the same data budget with less than 2. 0 points decrease in accuracy.
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
To democratize this, we train and release a family of large language models up to 16. 1B parameters, called CODEGEN, on natural language and programming language data, and open source the training library JAXFORMER.
Converse: A Tree-Based Modular Task-Oriented Dialogue System
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
Long Document Summarization with Top-down and Bottom-up Inference
Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.
Ranked #1 on
Text Summarization
on Pubmed
Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering
Among several interesting findings, it is important to highlight that (1) the generative readers perform better in long context QA, (2) the extractive readers perform better in short context while also showing better out-of-domain generalization, and (3) the encoder of encoder-decoder PrLMs (e. g., T5) turns out to be a strong extractive reader and outperforms the standard choice of encoder-only PrLMs (e. g., RoBERTa).
Efficient and Differentiable Conformal Prediction with General Function Classes
Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly over existing approaches in several applications such as prediction intervals with improved length, minimum-volume prediction sets for multi-output regression, and label prediction sets for image classification.
Dense Hierarchical Retrieval for Open-Domain Question Answering
In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework that can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage.
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
We first show that this chaotic behavior exists even along the training optimization trajectory of a single model, and propose a simple model averaging protocol that both significantly boosts domain generalization and diminishes the impact of stochasticity by improving the rank correlation between the in-domain validation accuracy and out-domain test accuracy, which is crucial for reliable early stopping.
Ranked #4 on
Domain Generalization
on TerraIncognita
Long Document Summarization with Top-Down and Bottom-Up Representation Inference
Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents.
Merlion: A Machine Learning Library for Time Series
We introduce Merlion, an open-source machine learning library for time series.
RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering
We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability.
Focused Attention Improves Document-Grounded Generation
Document grounded generation is the task of using the information provided in a document to improve text generation.
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.
Ranked #2 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Unsupervised Paraphrasing with Pretrained Language Models
To enforce a surface form dissimilar from the input, whenever the language model emits a token contained in the source sequence, DB prevents the model from outputting the subsequent source token for the next generation step.
Online Structured Meta-learning
When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks.
Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
We propose Deep Autoencoding Predictive Components (DAPC) -- a self-supervised representation learning method for sequence data, based on the intuition that useful representations of sequence data should exhibit a simple structure in the latent space.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications.
Ranked #5 on
Online Action Detection
on THUMOS'14
Fast and Robust Unsupervised Contextual Biasing for Speech Recognition
A common framework is to dynamically construct a small language model from the provided contextual mini corpus and interpolate its score with the main language model during the decoding process.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
An investigation of phone-based subword units for end-to-end speech recognition
For Switchboard, our phone-based BPE system achieves 6. 8\%/14. 4\% word error rate (WER) on the Switchboard/CallHome portion of the test set while joint decoding achieves 6. 3\%/13. 3\% WER.
Differentially Private Deep Learning with Smooth Sensitivity
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Near-Zero-Cost Differentially Private Deep Learning with Teacher Ensembles
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice.
Private Deep Learning with Teacher Ensembles
Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information.
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks.
Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
In low-resource supervised setting, the results show that our approach improves absolute performance by 14% and 4% when adapting SVHN to MNIST and vice versa, respectively, which outperforms unsupervised domain adaptation methods that require high-resource unlabeled target domain.
End-to-End Dense Video Captioning with Masked Transformer
To address this problem, we propose an end-to-end transformer model for dense video captioning.
Ranked #11 on
Video Captioning
on YouCook2
A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources.
Improved Regularization Techniques for End-to-End Speech Recognition
We augment audio data through random perturbations of tempo, pitch, volume, temporal alignment, and adding random noise. We further investigate the effect of dropout when applied to the inputs of all layers of the network.
Improving End-to-End Speech Recognition with Policy Learning
However, there is usually a disparity between the negative maximum likelihood and the performance metric used in speech recognition, e. g., word error rate (WER).
Ranked #49 on
Speech Recognition
on LibriSpeech test-clean
Spelling Correction as a Foreign Language
In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework.
On Optimality Conditions for Auto-Encoder Signal Recovery
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost.
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks.
Maximum Entropy Binary Encoding for Face Template Protection
In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face authentication.
Deep Secure Encoding: An Application to Face Recognition
In this paper we present Deep Secure Encoding: a framework for secure classification using deep neural networks, and apply it to the task of biometric template protection for faces.
Why Regularized Auto-Encoders learn Sparse Representation?
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks.
Parallel Feature Selection Inspired by Group Testing
Superior performance of our method is demonstrated on a challenging relation extraction task from a very large data set that have both redundant features and sample size in the order of millions.
Is Joint Training Better for Deep Auto-Encoders?
But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers.
Challenges in Representation Learning: A report on three machine learning contests
The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge.
Ranked #12 on
Facial Expression Recognition (FER)
on FER2013
