Search Results for author:
Found 19 papers, 8 papers with code
基于熵的二语语音习得评价研究—以日本学习者习得汉语声母为例(An Entropy-based Evaluation of L2 Speech Acquisition: The Preliminary Report on Chinese Initials Produced by Japanese Learners)
“本文引入“熵”对学习者二语音素发音错误的分布情况进行了量化研究。通过对不同音素及不同二语水平学习者音素错误率和错误分散度的分析发现:1. 错误率与错误分散度有较高的相关性, 二者的差异反映出错误分布的差异性;2. 错误率类似的音素中, 与母语音素相似度越高的音素错误分散度越小;3. 较初级水平, 中级水平学习者音素错误率下降而错误分散度上升。由此可见, 熵可以在错误率基础上可以进一步揭示学习者母语音系及二语水平对音素发音错误分散度的影响。”
Making Large Language Models Better Reasoners with Alignment
To address this problem, we introduce an \textit{Alignment Fine-Tuning (AFT)} paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss.
Soft Language Clustering for Multilingual Model Pre-training
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size.
Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis
Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence.
Large Language Models are not Fair Evaluators
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e. g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models.
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates.
Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion
However, unlike other image-text multimodal tasks, video has longer multimodal sequences with more redundancy and noise in both visual and audio modalities.
Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization
Also, Bi-Drop needs only one mini-batch to estimate the sub-net so it achieves higher utility of training data.
Enhancing Continual Relation Extraction via Classifier Decomposition
In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded.
DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog
Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios.
DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition
We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER).
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection
While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance.
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
In this paper, through empirical studies we argue that this assumption may not hold, and an important reason for catastrophic forgetting is that the learned representations do not have good robustness against the appearance of analogous relations in the subsequent learning process.
Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach
2) Balanced Tuning (BT) finetunes the model on the balanced memory data.
Text-Aware End-to-end Mispronunciation Detection and Diagnosis
In the field of assessing the pronunciation quality of constrained speech, the given transcriptions can play the role of a teacher.
HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification
However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potentials of PLMs can not be fully tapped.
Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU
With all these modifications, the size of the PHASEN model is shrunk from 33M parameters to 5M parameters, while the performance on VoiceBank+DEMAND is improved to the CSIG score of 4. 30, the PESQ score of 3. 07 and the COVL score of 3. 73.
A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augmentation Techniques
Recently, end-to-end mispronunciation detection and diagnosis (MD&D) systems has become a popular alternative to greatly simplify the model-building process of conventional hybrid DNN-HMM systems by representing complicated modules with a single deep network architecture.
