Search Results for author:
Found 14 papers, 7 papers with code
Addressing the Length Bias Problem in Document-Level Neural Machine Translation
To solve the length bias problem, we propose to improve the DNMT model in training method, attention mechanism, and decoding strategy.
Enhancing Neural Machine Translation with Semantic Units
Conventional neural machine translation (NMT) models typically use subwords and words as the basic units for model input and comprehension.
Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions
Specifically, we propose two methods to search the low forgetting risk regions, which are based on the curvature of loss and the impacts of the parameters on the model output, respectively.
Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings
The many-to-many multilingual neural machine translation can translate between language pairs unseen during training, i. e., zero-shot translation.
Importance-based Neuron Allocation for Multilingual Neural Machine Translation
Multilingual neural machine translation with a single model has drawn much attention due to its capability to deal with multiple languages.
Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation
Meanwhile, we force the conventional decoder to simulate the behaviors of the seer decoder via knowledge distillation.
Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
Domain Adaptation is widely used in practical applications of neural machine translation, which aims to achieve good performance on both the general-domain and in-domain.
Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation
The investigation on the modules of the NMT model shows that some modules have tight relation with the general-domain knowledge while some other modules are more essential in the domain adaptation.
Token-level Adaptive Training for Neural Machine Translation
The vanilla NMT model usually adopts trivial equal-weighted objectives for target tokens with different frequencies and tends to generate more high-frequency tokens and less low-frequency tokens compared with the golden token distribution.
Robust Neural Machine Translation with ASR Errors
In this paper, we propose a method to handle the two problems so as to generate robust translation to ASR errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution.
Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations.
Improving Multi-Head Attention with Capsule Networks
Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance.
Improving Domain Adaptation Translation with Domain Invariant and Specific Information
Besides, we add a discriminator to the shared encoder and employ adversarial training for the whole model to reinforce the performance of information separation and machine translation simultaneously.
