Mixture-of-experts (MoE) architecture has been proven a powerful method for
diverse tasks in training deep models in many applications. However, current
MoE implementations are task agnostic, treating all tokens from different tasks
in the same manner. In this work, we instead design a novel method that
incorporates task information into MoE models at different granular levels with
shared dynamic task-based adapters. Our experiments and analysis show the
advantages of our approaches over the dense and canonical MoE models on
multi-task multilingual machine translations. With task-specific adapters, our
models can additionally generalize to new tasks efficiently.

我们设计了一种新方法，将任务信息与 Mixture-of-experts 模型结合，通过共享的动态任务适配器在不同粒度级别上将任务信息融入模型中。实验证明，相比密集和经典的 Mixture-of-experts 模型，在多任务多语言机器翻译上，我们的方法具有优势。通过任务特定的适配器，我们的模型能够高效地泛化到新任务中。

基于任务的 MoE 多任务多语言机器翻译

Task-Based MoE for Multitask Multilingual Machine Translation

ChatGPT shows remarkable capabilities for machine translation (MT). Several
prior studies have shown that it achieves comparable results to commercial
systems for high-resource languages, but lags behind in complex tasks, e.g,
low-resource and distant-language-pairs translation. However, they usually
adopt simple prompts which can not fully elicit the capability of ChatGPT. In
this report, we aim to further mine ChatGPT's translation ability by revisiting
several aspects: temperature, task information, and domain information, and
correspondingly propose two (simple but effective) prompts: Task-Specific
Prompts (TSP) and Domain-Specific Prompts (DSP). We show that: 1) The
performance of ChatGPT depends largely on temperature, and a lower temperature
usually can achieve better performance; 2) Emphasizing the task information
further improves ChatGPT's performance, particularly in complex MT tasks; 3)
Introducing domain information can elicit ChatGPT's generalization ability and
improve its performance in the specific domain; 4) ChatGPT tends to generate
hallucinations for non-English-centric MT tasks, which can be partially
addressed by our proposed prompts but still need to be highlighted for the
MT/NLP community. We also explore the effects of advanced in-context learning
strategies and find a (negative but interesting) observation: the powerful
chain-of-thought prompt leads to word-by-word translation behavior, thus
bringing significant translation degradation.

本文旨在通过重新审视温度、任务信息和领域信息等方面，提出两种简单但有效的提示：任务特定提示 (TSP) 和领域特定提示 (DSP)，以进一步挖掘 ChatGPT 的翻译能力。我们表明：1) ChatGPT 的性能很大程度上取决于温度，较低的温度通常可以取得更好的性能；2) 强调任务信息可以进一步提高 ChatGPT 的性能，尤其是在复杂的机器翻译任务中；3) 引入领域信息可以引出 ChatGPT 的泛化能力，并提高其在特定领域的性能；4) 对于非英文中心的机器翻译任务，ChatGPT 倾向于产生幻觉，我们的提示可以部分解决这个问题，但仍需引起机器翻译 / 自然语言处理社区的重视。我们还探讨了高阶上下文学习策略的影响，发现一个 (负但有趣的) 观察结果：强大的思维链提示会导致逐字逐句的翻译行为，从而带来显著的翻译降解。

优化 ChatGPT 在机器翻译中的应用

Towards Making the Most of ChatGPT for Machine Translation

Humans achieve efficient learning by relying on prior knowledge about the
structure of naturally occurring tasks. There is considerable interest in
designing reinforcement learning (RL) algorithms with similar properties. This
includes proposals to learn the learning algorithm itself, an idea also known
as meta learning. One formal interpretation of this idea is as a partially
observable multi-task RL problem in which task information is hidden from the
agent. Such unknown task problems can be reduced to Markov decision processes
(MDPs) by augmenting an agent's observations with an estimate of the belief
about the task based on past experience. However estimating the belief state is
intractable in most partially-observed MDPs. We propose a method that
separately learns the policy and the task belief by taking advantage of various
kinds of privileged information. Our approach can be very effective at solving
standard meta-RL environments, as well as a complex continuous control
environment with sparse rewards and requiring long-term memory.

本文提出一种在元强化学习中用于解决任务信息受限问题的方法，通过利用各种特权信息，分别学习策略和任务信念来解决部分可观测马尔可夫决策问题，从而在元强化学习环境中较为有效地解决标准问题和需要长期记忆的复杂连续控制问题。