Search Results for author:
Found 12 papers, 4 papers with code
DESED: Dialogue-based Explanation for Sentence-level Event Detection
Many recent sentence-level event detection efforts focus on enriching sentence semantics, e. g., via multi-task or prompt-based learning.
MT-Speech at SemEval-2022 Task 10: Incorporating Data Augmentation and Auxiliary Task with Cross-Lingual Pretrained Language Model for Structured Sentiment Analysis
Furthermore, we leverage two data augment strategies and auxiliary tasks to improve the performance on few-label data and zero-shot cross-lingual settings.
Dialog-to-Actions: Building Task-Oriented Dialogue System via Action-Level Generation
End-to-end generation-based approaches have been investigated and applied in task-oriented dialogue systems.
MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
As a pioneering exploration that expands event detection to the scenarios involving informal and heterogeneous texts, we propose a new large-scale Chinese event detection dataset based on user reviews, text conversations, and phone conversations in a leading e-commerce platform for food service.
Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization
To reduce the peak latency, we propose a simple and novel method named peak-first regularization, which utilizes a frame-wise knowledge distillation function to force the probability distribution of the CTC model to shift left along the time axis instead of directly modifying the calculation process of CTC loss and gradients.
A Low-Cost, Controllable and Interpretable Task-Oriented Chatbot: With Real-World After-Sale Services as Example
Though widely used in industry, traditional task-oriented dialogue systems suffer from three bottlenecks: (i) difficult ontology construction (e. g., intents and slots); (ii) poor controllability and interpretability; (iii) annotation-hungry.
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
The simulation module is jointly trained with the ASR model using a self-supervised loss; the ASR model is optimized with the usual ASR loss, e. g., CTC-CRF as used in our experiments.
An Empirical Study of Language Model Integration for Transducer based Speech Recognition
Based on the DR method, we propose a low-order density ratio method (LODR) by replacing the estimation with a low-order weak language model.
Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss
Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.
Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Moreover, the explicit prosody features used in the prosody predicting module can increase the diversity of synthetic speech by adjusting the value of prosody features.
Density-Based Dynamic Curriculum Learning for Intent Detection
To handle this problem, we propose a density-based dynamic curriculum learning model.
Learning Speaker Embedding with Momentum Contrast
Momentum Contrast (MoCo) is a recently proposed unsupervised representation learning framework, and has shown its effectiveness for learning good feature representation for downstream vision tasks.
