Papers by Chenze Shao
Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Neural networks tend to gradually forget the previously learned knowledge when learning multiple tasks sequentially from dynamic data distributions. |
| Approach: | They propose a method that iteratively provides complementary knowledge to student models by dynamically updating teacher models trained on specific data orders. |
| Outcome: | The proposed method improves on multiple machine translation tasks and improves performance over baseline systems. |
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed. |
| Approach: | They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer. |
| Outcome: | The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup. |
Generating Diverse Translation from Model Distribution with Dropout (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural machine translation models lack diversity in their generation. |
| Approach: | They propose to generate diverse translations by deriving Bayesian models and sampling models from them for inference. |
| Outcome: | The proposed method makes a better trade-off between diversity and accuracy. |
Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation models are usually based on attention-based encoder-decoder frameworks. |
| Approach: | They introduce a seer decoder into the encoder-decoder framework during training . they force the conventional decoded decodes to simulate the behavior of the seer . |
| Outcome: | The proposed method outperforms baselines on Chinese, English and German translation tasks. |
Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Non-autoregressive models lack the ability to capture sequential dependency . Existing approaches to model sequential dependency have to apply a sequential decision process at inference time . |
| Approach: | They propose a Viterbi decoding framework to capture sequential dependency . they propose to find the optimal translation path under any length constraint . |
| Outcome: | The proposed framework improves the performance of DA-Transformer while maintaining similar speedup. |
Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective (2024.acl-long)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has made remarkable progress over the past years, but under-translation and over-translatation remain challenging obstacles faced by NMT systems. |
| Approach: | They propose to employ the confidence of predicting the end of sentence (EOS) as a detector for under-translation and strengthen the confidence-based penalty to penalize candidates with a high risk of under-translated. |
| Outcome: | The proposed method can detect and rectify under-translated outputs, with minor impact on other correct translations. |
Non-autoregressive Streaming Transformer for Simultaneous Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Simultaneous machine translation models are trained to strike a balance between latency and translation quality. |
| Approach: | They propose a non-autoregressive streaming Transformer which generates blank tokens and decodes repetitive tokens to adjust its READ/WRITE strategy flexibly. |
| Outcome: | The proposed model outperforms previous strong autoregressive models on various benchmarks on siMT. |
Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation models are usually trained with word-level loss under teacher forcing algorithm . however, this method suffers from exposure bias due to high variance of gradient estimation . |
| Approach: | They propose a method with a differentiable sequence-level training objective . they use greedy search to alleviate the problem of exposure bias . |
| Outcome: | Experiments on Chinese-to-English translation tasks show that the proposed method outperforms the reinforcement-based methods. |
Non-Autoregressive Models for Fast Sequence Generation (2022.emnlp-tutorials)
Copied to clipboard
| Challenge: | Autoregressive (AR) models can only generate target sequence word-by-word due to the AR mechanism and suffer from slow inference. |
| Approach: | This tutorial provides an introduction to non-autoregressive sequence generation. |
| Outcome: | This tutorial explains how to generate non-autoregressive sequence generation models. |
Instruction Position Matters in Sequence Generation with Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) can perform conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. |
| Approach: | They propose to shift the position of task instructions after the input sentences to enhance the model's instruction-following capability. |
| Outcome: | The proposed method outperforms traditional settings across various model scales (1B / 7B & 13B) and different sequence generation tasks (translation and summarization) without any additional data or annotation costs. |
One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing non-autoregressive neural machine translation models suffer from multimodality problem . multi-modality is not solved by a teacher forcing algorithm, limiting model capability . |
| Approach: | They propose a method that generates multiple reference translations for each source sentence . they compare the NAT output with all references and select the one that best fits the simulated model . |
| Outcome: | The proposed method achieves 29.82 BLEU with only one decoding pass on WMT14 En-De . |