Task-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can they know where the system is failing and needs more training data or new functionality? In this work, we study ways in which realistic user utterances can be generated synthetically, to help increase the linguistic and functional coverage of the system, without compromising the privacy of actual users. To this end, we propose a two-stage Differentially Private (DP) generation method which first generates latent semantic parses, and then generates utterances based on the parses. Our proposed approach improves MAUVE by 3.8$\times$ and parse tree node-type overlap by 1.4$\times$ relative to current approaches for private synthetic data generation, improving both on fluency and semantic coverage. We further validate our approach on a realistic domain adaptation task of adding new functionality from private user data to a semantic parser, and show gains of 1.3$\times$ on its accuracy with the new feature.

Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases, probability mass can ``leak'' onto the set of infinite sequences. In order to characterize the notion of leakage more precisely, this paper offers a measure-theoretic treatment of language modeling. We prove that many popular language model families are in fact tight, meaning that they will not leak in this sense. We also generalize characterizations of tightness proposed in previous works.

在现实世界中的对话系统中，生成的响应必须满足几个互锁的限制：内容丰富，真实且易于控制。语言生成中的两个主要范式 - 神经语言建模和基于规则的一代 - 都难以满足这些约束。即使是最好的神经模型，也容易出现信息的幻觉和省略，而现有的基于规则的形式的形式使得很难编写既灵活又流利的语法。我们描述了对话响应产生的混合体系结构，结合了两种方法的优势。该体系结构有两个组件。首先，使用新的正式框架定义的基于规则的内容选择模型，称为数据流转导，该模型使用声明性规则将对话代理的计算（表示为数据流图）转换为代表上下文可接受响应空间的无上下文语法。其次，使用这些语法来限制神经语言模型的输出的受约束解码过程，该过程选择流利的话语。最终的系统在人类对流利，相关性和真实性的评估中的表现都优于基于规则的方法和学识渊博的方法。

酒吧 - 希利尔的结构是正式语言理论的经典结果。它通过构造表明，无上下文语言与普通语言之间的相交本身是无上下文的。但是，其原始配方（Bar-Hillel等人，1961年）都不是其加权扩展（Nederhof和Satta，2003年）都无法使用$ \ epsilon $ -Arcs处理自动机。在此简短的说明中，我们将Bar-Hillel结构概括为即使自动机包含$ \ epsilon $ -Arcs，也可以正确计算交叉路口。我们进一步证明，我们的广义结构导致语法编码输入自动机和语法的结构，同时保留原始结构的渐近尺寸。

我们介绍了BenchClamp，这是一种评估受约束语言模型解析的基准测试，该基准通过通过限制性解码的启动或微调语言模型来基于输入文本的分析来产生语义输出。目前，预审前语言模型的开发人员基于分类，跨度提取和自由文本生成任务。语言解析在语言模型评估中被忽略，因为处理特定于任务的体系结构和表示的复杂性。最近的工作表明，当输出被限制为有效的语义表示时，从提示或微调的语言模型中产生的发电能力可以很好地表现。台式设备包括无上下文的语法，适用于六个具有不同输出含义表示形式的语义解析数据集，以及一个受约束的解码接口，以生成这些语法覆盖的输出。我们为每个数据集提供低，中和高资源分割，从而可以在不同的数据制度下准确比较各种语言模型。我们的基准测试既支持基于及时的学习又支持微调，并为语言模型开发人员提供了易于使用的工具包，以评估语义解析。

In natural language understanding (NLU) production systems, users' evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning representation space. This requires additional training data and results in ever-growing datasets. We present the first systematic investigation of this incremental symbol learning scenario. Our analysis reveals a troubling quirk in building broad-coverage NLU systems: as the training dataset grows, performance on the new symbol often decreases if we do not accordingly increase its training data. This suggests that it becomes more difficult to learn new symbols with a larger training dataset. We show that this trend holds for multiple mainstream models on two common NLU tasks: intent recognition and semantic parsing. Rejecting class imbalance as the sole culprit, we reveal that the trend is closely associated with an effect we call source signal dilution, where strong lexical cues for the new symbol become diluted as the training dataset grows. Selectively dropping training examples to prevent dilution often reverses the trend, showing the over-reliance of mainstream neural NLU models on simple lexical cues. Code, models, and data are available at https://aka.ms/nlu-incremental-symbol-learning

我们提出了一种建模不规则间隔的离散事件序列的方法。我们从变压器的连续时间变型开始，最初制定（Vaswani等，2017）用于没有时间戳的序列。我们在时间$ T $嵌入可能的事件（或其他布尔事实）通过注意在时间$ <T $（以及它们发生时为真实的事实）的事件上。我们使用模式匹配的逻辑规则来控制此关注，这些规则与共享与会者的事件和事实相关。这些规则确定将参加哪些先前的事件，以及如何将事件和事实的嵌入式转换为注意力查询，键和值。其他逻辑规则描述了如何以响应事件更改集事集。我们的方法密切关注Mei等人。 （2020A），并通过时间形式主义进行逻辑规则的时间正式主义。与那样一样，域专家首先写一组逻辑规则，每个逻辑规则在每次$ t $时都建立一个可能的事件和其他事实。每个可能的事件或其他事实都是使用从建立它的规则派生的神经结构嵌入。我们与Mei等人的唯一区别。 （2020A）是，我们得出了一个更平坦的关注的神经结构，而他们使用了更多的串行LSTM架构。我们发现我们的注意力的方法在Robocup数据集中表现得同样良好，逻辑规则在提高性能方面发挥着重要作用。我们还将这两种方法与两种以前的基于关注的方法进行了比较（Zuo等，2020; Zhang等，2020A），在没有逻辑规则的情况下更简单的合成和真实域，并发现我们所提出的方法至少是好的，而有时比其他三种方法中的每一种更好。

我们探索使用大型预用语言模型作为少量语义解析器。语义解析中的目标是给定自然语言输入的结构化含义表示。但是，培训语言模型以生成自然语言。为了弥合差距，我们使用语言模型来解释进入一个类似于英语的受控的子宫内的输入，可以自动映射到目标含义表示表示。我们的结果表明，只有少量的数据和较少的代码转换为类似英语的代表，我们为快速启动语义解析器的蓝图导致了对多个社区任务的令人惊讶的有效性能，大大超过基线方法也在相同的限制上培训数据。

While inferring common actor states (such as position or velocity) is an important and well-explored task of the perception system aboard a self-driving vehicle (SDV), it may not always provide sufficient information to the SDV. This is especially true in the case of active emergency vehicles (EVs), where light-based signals also need to be captured to provide a full context. We consider this problem and propose a sequential methodology for the detection of active EVs, using an off-the-shelf CNN model operating at a frame level and a downstream smoother that accounts for the temporal aspect of flashing EV lights. We also explore model improvements through data augmentation and training with additional hard samples.

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.