265 citations · 1.9k across the 79 of their papers we have counts for
79 papers
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
Yung-Sung Chuang, Rumen Dangovski, Hongyin Luo +7
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between…
WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
Heting Gao, Junrui Ni, Kaizhi Qian +3
Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text example…
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
Kaizhi Qian, Yang Zhang, Heting Gao +5
Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to do…
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection
Minqian Liu, Shiyu Chang, Lifu Huang
Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge i…
Adversarial Support Alignment
Shangyuan Tong, Timur Garipov, Yang Zhang +2
We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matc…
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
Junrui Ni, Liming Wang, Heting Gao +4
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untra…
On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis
Cheng-I Jeff Lai, Erica Cooper, Yang Zhang +8
Are end-to-end text-to-speech (TTS) models over-parametrized? To what extent can these models be pruned, and what happens to their synthesis capabilities? This work serves as a sta…
Understanding Interlocking Dynamics of Cooperative Rationalization
Mo Yu, Yang Zhang, Shiyu Chang +1
Selective rationalization explains the prediction of complex neural networks by finding a small subset of the input that is sufficient to predict the neural model output. The selec…
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding
Sijia Wang, Mo Yu, Shiyu Chang +2
Event extraction is typically modeled as a multi-class classification problem where event types and argument roles are treated as atomic symbols. These approaches are usually limit…
Global Rhythm Style Transfer Without Text Transcriptions
Kaizhi Qian, Yang Zhang, Shiyu Chang +4
Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody…
Learning Stable Classifiers by Transferring Unstable Features
Yujia Bao, Shiyu Chang, Regina Barzilay
While unbiased machine learning models are essential for many applications, bias is a human-defined concept that can vary across tasks. Given only input-label pairs, algorithms may…
PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
Cheng-I Jeff Lai, Yang Zhang, Alexander H. Liu +7
Self-supervised speech representation learning (speech SSL) has demonstrated the benefit of scale in learning rich representations for Automatic Speech Recognition (ASR) with limit…
Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
Yujia Bao, Shiyu Chang, Regina Barzilay
We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using…
Complementary Evidence Identification in Open-Domain Question Answering
Xiangyang Mou, Mo Yu, Shiyu Chang +3
This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). The problem aims to efficiently find a small set of passages tha…
Generating Adversarial Computer Programs using Optimized Obfuscations
Shashank Srikant, Sijia Liu, Tamara Mitrovska +4
Machine learning (ML) models that learn and predict properties of computer programs are increasingly being adopted and deployed. These models have demonstrated success in applicati…
TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
Yifan Jiang, Shiyu Chang, Zhangyang Wang
The recent explosive interest on transformers has suggested their potential to become powerful "universal" models for computer vision tasks, such as classification, detection, and…
Self-Progressing Robust Training
Minhao Cheng, Pin-Yu Chen, Sijia Liu +3
Enhancing model robustness under new and even adversarial environments is a crucial milestone toward building trustworthy machine learning systems. Current robust training methods…
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
Tianlong Chen, Jonathan Frankle, Shiyu Chang +4
The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervis…
Training Stronger Baselines for Learning to Optimize
Tianlong Chen, Weiyi Zhang, Jingyang Zhou +4
Learning to optimize (L2O) has gained increasing attention since classical optimizers require laborious problem-specific design and hyperparameter tuning. However, there is a gap b…
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
Xiaoxiao Guo, Mo Yu, Yupeng Gao +3
Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. In contrast to previous text g…
Lifelong Object Detection
Wang Zhou, Shiyu Chang, Norma Sosa +2
Recent advances in object detection have benefited significantly from rapid developments in deep neural networks. However, neural networks suffer from the well-known issue of catas…
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
Tianlong Chen, Jonathan Frankle, Shiyu Chang +4
In natural language processing (NLP), enormous pre-trained models like BERT have become the standard starting point for training on a range of downstream tasks, and similar trends…
Proper Network Interpretability Helps Adversarial Robustness in Classification
Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang +4
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visual…
Can 3D Adversarial Logos Cloak Humans?
Yi Wang, Jingyang Zhou, Tianlong Chen +4
With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-w…