Search Results for author:
Found 33 papers, 9 papers with code
Personalized Search-based Query Rewrite System for Conversational AI
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect.
Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation
Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting.
OPPO’s Machine Translation Systems for WMT20
In this paper we demonstrate our (OPPO’s) machine translation systems for the WMT20 Shared Task on News Translation for all the 22 language pairs.
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems
Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e. g. users’ implicit feedback).
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
The Mininglamp Machine Translation System for WMT21
This paper describes Mininglamp neural machine translation systems of the WMT2021 news translation tasks.
SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
Moreover, SafeSpeech has real-time capability in real-world tests.
Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
To address this limitation and protect live users' speech against ASR systems, we propose a novel framework, AudioShield.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
We evaluate our approach on three modern ASR models, and the experimental results demonstrate that our method significantly improves the transferability of adversarial examples generated by previous methods while preserving the audio quality.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Given the pretrained language model whose weight is frozen, our algorithm aims to learn two levels of adaptation simultaneously: the first level aims to learn a common adapter for all clients, while the second level fosters individual client personalization.
On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness
In particular, we study stochastic bilevel optimization problems where the lower-level function is strongly convex and the upper-level objective is nonconvex with potentially unbounded smoothness.
A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
This complexity result is nearly optimal up to logarithmic factors without mean-square smoothness of the stochastic gradient oracle.
Embodied Image Quality Assessment for Robotic Intelligence
Image quality assessment (IQA) of user-generated content (UGC) is a critical technique for human quality of experience (QoE).
MVKTrans: Multi-View Knowledge Transfer for Robust Multiomics Classification
In this paper, we propose the multi-view knowledge transfer learning (MVKTrans) framework, which transfers intra- and inter-omics knowledge in an adaptive manner by reviewing data heterogeneity and suppressing bias transfer, thereby enhancing classification performance.
Mitigating Unauthorized Speech Synthesis for Voice Protection
With just a few speech samples, it is possible to perfectly replicate a speaker's voice in recent years, while malicious voice exploitation (e. g., telecom fraud for illegal financial gain) has brought huge hazards in our daily lives.
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
We prove that our algorithm achieves an oracle complexity of $\widetilde{O}(1/\epsilon^3)$ to find an $\epsilon$-stationary point, when the lower-level stochastic gradient's variance is $O(\epsilon)$.
Multiobjective Vehicle Routing Optimization with Time Windows: A Hybrid Approach Using Deep Reinforcement Learning and NSGA-II
Notably, the weight-aware strategy significantly reduces the training time of DRL while achieving better results, enabling a single DRL model to solve the entire multiobjective optimization problem.
STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering
In this paper, we propose STOC-TOT, a stochastic tree-of-thought reasoning prompting method with constrained decoding for MHQA and conduct a detailed comparison with other reasoning prompts on different question types and reasoning types.
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
In this paper, we propose an attack on ASR systems based on user-customized style transfer.
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
When the upper-level problem is nonconvex and unbounded smooth, and the lower-level problem is strongly convex, we prove that our algorithm requires $\widetilde{\mathcal{O}}(1/\epsilon^4)$ iterations to find an $\epsilon$-stationary point in the stochastic setting, where each iteration involves calling a stochastic gradient or Hessian-vector product oracle.
Multiobjective Hydropower Reservoir Operation Optimization with Transformer-Based Deep Reinforcement Learning
Due to shortage of water resources and increasing water demands, the joint operation of multireservoir systems for balancing power generation, ecological protection, and the residential water supply has become a critical issue in hydropower management.
PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding
Conversational understanding is an integral part of modern intelligent devices.
Improving Mandarin Speech Recogntion with Block-augmented Transformer
In this work, we believe that the output information of each block in the encoder and decoder is not completely inclusive, in other words, their output information may be complementary.
Ranked #8 on
Speech Recognition
on AISHELL-1
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Robust Dialogue Utterance Rewriting as Sequence Tagging
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.
XLP at SemEval-2020 Task 9: Cross-lingual Models with Focal Loss for Sentiment Analysis of Code-Mixing Language
In this paper, we present an approach for sentiment analysis in code-mixed language on twitter defined in SemEval-2020 Task 9.
OPPO's Machine Translation System for the IWSLT 2020 Open Domain Translation Task
In this paper, we demonstrate our machine translation system applied for the Chinese-Japanese bidirectional translation task (aka.
Multi-Granularity Self-Attention for Neural Machine Translation
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information.
Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
Recent studies have shown that a hybrid of self-attention networks (SANs) and recurrent neural networks (RNNs) outperforms both individual architectures, while not much is known about why the hybrid models work.
Modeling Recurrence for Transformer
In addition to the standard recurrent neural network, we introduce a novel attentive recurrent network to leverage the strengths of both attention and recurrent networks.
Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition
The layers between the source and target feature extractor are partially untied during the training stage to take both training efficiency and domain adaptation into consideration.
