用 Babylon 变革自然语言理解：面向自动得来速点餐的实时、边缘高效、多意图翻译系统开发案例研究
Transforming NLU with Babylon: A Case Study in Development of Real-time, Edge-Efficient, Multi-Intent Translation System for Automated Drive-Thru Ordering
AI总结：
针对自动得来速点餐场景，提出将自然语言理解建模为意图翻译任务的Transformer架构Babylon，并引入LSTM音素池化以降低输入长度、提升边缘实时性与ASR鲁棒性，实验表明其在准确率、延迟和内存上优于Flan-T5与BART。
摘要：
实时对话式 AI 智能体在动态户外环境（如自动得来速系统）中执行自然语言理解（NLU）面临挑战。这些环境要求 NLU 模型能够处理背景噪声、多样化口音和多意图查询，同时在边缘设备上满足严格的延迟和内存约束。此外，对上游自动语音识别（ASR）错误的鲁棒性至关重要，因为这些环境中的 ASR 输出通常含有噪声。我们提出 Babylon，一种基于 Transformer 的架构，将 NLU 作为意图翻译任务来处理，把自然语言输入转换为规则语言单元（“transcodes”）序列，这些单元同时编码意图和槽位信息。这种形式化方法使 Babylon 能够在单轮对话中处理多意图场景。此外，Babylon 结合了基于 LSTM 的 token 池化机制来预处理音素序列，缩短输入长度并针对低延迟、低内存的边缘部署进行优化。这也有助于减轻 ASR 输出中的不准确性，增强系统鲁棒性。虽然本工作聚焦于得来速点餐，但 Babylon 的设计可扩展到类似的易受噪声影响的场景，例如售票自助终端。我们的实验表明，与 Flan-T5 和 BART 等常用的神经机器翻译（NMT）模型相比，Babylon 在准确率-延迟-内存占用权衡方面取得了显著更优的效果，证明了其在边缘部署环境中用于实时 NLU 的有效性。
英文摘要：
Real-time conversational AI agents face challenges in performing Natural Language Understanding (NLU) in dynamic, outdoor environments like automated drive-thru systems. These settings require NLU models to handle background noise, diverse accents, and multi-intent queries while operating under strict latency and memory constraints on edge devices. Additionally, robustness to errors from upstream Automatic Speech Recognition (ASR) is crucial, as ASR outputs in these environments are often noisy. We introduce Babylon, a transformer-based architecture that tackles NLU as an intent translation task, converting natural language inputs into sequences of regular language units ('transcodes') that encode both intents and slot information. This formulation allows Babylon to manage multi-intent scenarios in a single dialogue turn. Furthermore, Babylon incorporates an LSTM-based token pooling mechanism to preprocess phoneme sequences, reducing input length and optimizing for low-latency, low-memory edge deployment. This also helps mitigate inaccuracies in ASR outputs, enhancing system robustness. While this work focuses on drive-thru ordering, Babylon's design extends to similar noise-prone scenarios, for e.g. ticketing kiosks. Our experiments show that Babylon achieves significantly better accuracy-latency-memory footprint trade-offs over typically employed NMT models like Flan-T5 and BART, demonstrating its effectiveness for real-time NLU in edge deployment settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
