Active learning approaches to enhancing neural machine translation
Active learning is an efficient approach for mitigating data dependency when training neural
machine translation (NMT) models. In this paper, we explore new training frameworks by …
machine translation (NMT) models. In this paper, we explore new training frameworks by …
Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation
Conventional knowledge distillation (KD) approaches are commonly employed to compress
neural machine translation (NMT) models. However, they only obtain one lightweight …
neural machine translation (NMT) models. However, they only obtain one lightweight …
Exploring the intersection of large language models and agent-based modeling via prompt engineering
E Junprung - arXiv preprint arXiv:2308.07411, 2023 - arxiv.org
The final frontier for simulation is the accurate representation of complex, real-world social
systems. While agent-based modeling (ABM) seeks to study the behavior and interactions of …
systems. While agent-based modeling (ABM) seeks to study the behavior and interactions of …
Guiding teacher forcing with seer forcing for neural machine translation
Although teacher forcing has become the main training paradigm for neural machine
translation, it usually makes predictions only conditioned on past information, and hence …
translation, it usually makes predictions only conditioned on past information, and hence …
Improved training of mixture-of-experts language gans
Despite the dramatic success in image generation, Generative Adversarial Networks (GANs)
still face great challenges in text generation. The difficulty in generator training arises from …
still face great challenges in text generation. The difficulty in generator training arises from …
Dualformer: a unified bidirectional sequence-to-sequence learning
JT Chien, WH Chang - ICASSP 2021-2021 IEEE International …, 2021 - ieeexplore.ieee.org
This paper presents a new dual domain mapping based on a unified bidirectional sequence-
to-sequence (seq2seq) learning. Traditionally, dual learning in domain mapping was …
to-sequence (seq2seq) learning. Traditionally, dual learning in domain mapping was …
Exploring iterative dual domain adaptation for neural machine translation
Abstract Domain adaptation for neural machine translation (NMT) has always been a hot
research topic in the community of machine translation. Generally, previous studies focus on …
research topic in the community of machine translation. Generally, previous studies focus on …
Collaborative learning of bidirectional decoders for unsupervised text style transfer
Unsupervised text style transfer aims to alter the underlying style of the text to a desired
value while keeping its style-independent semantics, without the support of parallel training …
value while keeping its style-independent semantics, without the support of parallel training …
Multi-agent mutual learning at sentence-level and token-level for neural machine translation
Mutual learning, where multiple agents learn collaboratively and teach one another, has
been shown to be an effective way to distill knowledge for image classification tasks. In this …
been shown to be an effective way to distill knowledge for image classification tasks. In this …
Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
Complex news events, such as natural disasters and socio-political conflicts, require swift
responses from the government and society. Relying on historical events to project the future …
responses from the government and society. Relying on historical events to project the future …