1.2k citations · 7.6k across the 154 of their papers we have counts for
35 papers · 1 filter
Towards Generating Real-World Time Series Data
Hengzhi Pei, Kan Ren, Yuqing Yang +3
Time series data generation has drawn increasing attention in recent years. Several generative adversarial network (GAN) based methods have been proposed to tackle the problem usua…
Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model
Liang He, Shizhuo Zhang, Lijun Wu +10
Understanding protein sequences is vital and urgent for biology, healthcare, and medicine. Labeling approaches are expensive yet time-consuming, while the amount of unlabeled data…
Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning
Jongjin Park, Younggyo Seo, Chang Liu +4
Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations. However, behavioral cloning often suffers from the causal…
Distributional Reinforcement Learning for Multi-Dimensional Reward Functions
Pushi Zhang, Xiaoyu Chen, Li Zhao +3
A growing trend for value-based reinforcement learning (RL) algorithms is to capture more information than scalar value functions in the value network. One of the most well-known m…
GNN is a Counter? Revisiting GNN for Question Answering
Kuan Wang, Yuyu Zhang, Diyi Yang +2
Question Answering (QA) has been a long-standing research topic in AI and NLP fields, and a wealth of studies have been conducted to attempt to equip QA systems with human-level re…
Discovering Drug-Target Interaction Knowledge from Biomedical Literature
Yutai Hou, Yingce Xia, Lijun Wu +6
The Interaction between Drugs and Targets (DTI) in human body plays a crucial role in biomedical science and applications. As millions of papers come out every year in the biomedic…
PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription
Chen Zhang, Jiaxing Yu, LuChin Chang +4
Automatic lyrics transcription (ALT), which can be regarded as automatic speech recognition (ASR) on singing voice, is an interesting and practical topic in academia and industry.…
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Yichong Leng, Xu Tan, Rui Wang +8
Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple ca…
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
Zeqian Ju, Peiling Lu, Xu Tan +7
Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodie…
Analyzing and Mitigating Interference in Neural Architecture Search
Jin Xu, Xu Tan, Kaitao Song +5
Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However…
A Survey on Neural Speech Synthesis
Xu Tan, Tao Qin, Frank Soong +1
Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning co…
A Survey on Low-Resource Neural Machine Translation
Rui Wang, Xu Tan, Renqian Luo +2
Neural approaches have achieved state-of-the-art accuracy on machine translation but suffer from the high cost of collecting large scale parallel data. Thus, a lot of research has…
AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style
Yuzi Yan, Xu Tan, Bohan Li +6
While recent text to speech (TTS) models perform very well in synthesizing reading-style (e.g., audiobook) speech, it is still challenging to synthesize spontaneous-style speech (e…
Supervised Off-Policy Ranking
Yue Jin, Yue Zhang, Tao Qin +4
Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a…
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
Mingliang Zeng, Xu Tan, Rui Wang +3
Symbolic music understanding, which refers to the understanding of music from the symbolic data (e.g., MIDI format, but not audio), covers many music applications such as genre cla…
On the Generative Utility of Cyclic Conditionals
Chang Liu, Haoyue Tang, Tao Qin +2
We study whether and how can we model a joint distribution using two conditional models and that form a cycle. This is motivated by the observation that…
R-Drop: Regularized Dropout for Neural Networks
Xiaobo Liang, Lijun Wu, Juntao Li +6
Dropout is a powerful and widely used technique to regularize the training of deep neural networks. In this paper, we introduce a simple regularization strategy upon dropout in mod…
Dual-view Molecule Pre-training
Jinhua Zhu, Yingce Xia, Tao Qin +3
Inspired by its success in natural language processing and computer vision, pre-training has attracted substantial attention in cheminformatics and bioinformatics, especially for m…
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Sang-gil Lee, Heeseung Kim, Chaehun Shin +7
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prio…
NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search
Jin Xu, Xu Tan, Renqian Luo +4
While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer fro…
Learning Structures for Deep Neural Networks
Jinhui Yuan, Fei Pan, Chunting Zhou +2
In this paper, we focus on the unsupervised setting for structure learning of deep neural networks and propose to adopt the efficient coding principle, rooted in information theory…
Exploiting Adapters for Cross-lingual Low-resource Speech Recognition
Wenxin Hou, Han Zhu, Yidong Wang +4
Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource…
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Yichong Leng, Xu Tan, Linchen Zhu +7
Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER) than original ASR…
AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data
Yuzi Yan, Xu Tan, Bohan Li +4
Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech a…