意图分类（IC）和插槽标签（SL）模型，它形成对话系统的基础，通常会在实际字环境中遇到噪声数据。在这项工作中，我们调查了强大的IC / SL模型是如何嘈杂的数据。我们在生产人机对话中发现七种常见噪声类型（缩写，套管，拼写错误，形态变体，释义，标点符号和同义词），我们收集并公开发布测试套件。在此测试套件上，我们表明普通噪声类型显着降低了最先进的基于伯特IC / SL模型的IC精度和SL F1性能。通过利用串噪声稳健性转移 - 对一种噪声类型的培训来提高另一种噪声类型的鲁棒性 - 我们设计综合数据增强方法，以增加所有七种噪声类型的模型性能+ 10.8％的IC精度和+15平均SL F1点。据我们所知，这是第一个展示单个IC / SL模型的工作，这是一个广泛的噪声现象。

我们提出了一个新的框架，在增强的自然语言（TANL）之间的翻译，解决了许多结构化预测语言任务，包括联合实体和关系提取，嵌套命名实体识别，关系分类，语义角色标记，事件提取，COREREFED分辨率和对话状态追踪。通过培训特定于特定于任务的鉴别分类器来说，我们将其作为一种在增强的自然语言之间的翻译任务，而不是通过培训问题，而不是解决问题，而是可以轻松提取任务相关信息。我们的方法可以匹配或优于所有任务的特定于任务特定模型，特别是在联合实体和关系提取（Conll04，Ade，NYT和ACE2005数据集）上实现了新的最先进的结果，与关系分类（偶尔和默示）和语义角色标签（Conll-2005和Conll-2012）。我们在使用相同的架构和超参数的同时为所有任务使用相同的架构和超级参数，甚至在培训单个模型时同时解决所有任务（多任务学习）。最后，我们表明，由于更好地利用标签语义，我们的框架也可以显着提高低资源制度的性能。

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.

A canonical algorithm for log-concave sampling is the Langevin Algorithm, aka the Langevin Diffusion run with some discretization stepsize $\eta > 0$. This discretization leads the Langevin Algorithm to have a stationary distribution $\pi_{\eta}$ which differs from the stationary distribution $\pi$ of the Langevin Diffusion, and it is an important challenge to understand whether the well-known properties of $\pi$ extend to $\pi_{\eta}$. In particular, while concentration properties such as isoperimetry and rapidly decaying tails are classically known for $\pi$, the analogous properties for $\pi_{\eta}$ are open questions with direct algorithmic implications. This note provides a first step in this direction by establishing concentration results for $\pi_{\eta}$ that mirror classical results for $\pi$. Specifically, we show that for any nontrivial stepsize $\eta > 0$, $\pi_{\eta}$ is sub-exponential (respectively, sub-Gaussian) when the potential is convex (respectively, strongly convex). Moreover, the concentration bounds we show are essentially tight. Key to our analysis is the use of a rotation-invariant moment generating function (aka Bessel function) to study the stationary dynamics of the Langevin Algorithm. This technique may be of independent interest because it enables directly analyzing the discrete-time stationary distribution $\pi_{\eta}$ without going through the continuous-time stationary distribution $\pi$ as an intermediary.

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. Language models are generally trained on the publicly available text and code and cannot be expected to directly generalize to domain-specific parsing tasks in a zero-shot setting. In this work, we propose ZEROTOP, a zero-shot task-oriented parsing method that decomposes a semantic parsing problem into a set of abstractive and extractive question-answering (QA) problems, enabling us to leverage the ability of LLMs to zero-shot answer reading comprehension questions. For each utterance, we prompt the LLM with questions corresponding to its top-level intent and a set of slots and use the LLM generations to construct the target meaning representation. We observe that current LLMs fail to detect unanswerable questions; and as a result, cannot handle questions corresponding to missing slots. To address this problem, we fine-tune a language model on public QA datasets using synthetic negative samples. Experimental results show that our QA-based decomposition paired with the fine-tuned LLM can correctly parse ~16% of utterances in the MTOP dataset without requiring any annotated data.

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.

From smoothly pursuing moving objects to rapidly shifting gazes during visual search, humans employ a wide variety of eye movement strategies in different contexts. While eye movements provide a rich window into mental processes, building generative models of eye movements is notoriously difficult, and to date the computational objectives guiding eye movements remain largely a mystery. In this work, we tackled these problems in the context of a canonical spatial planning task, maze-solving. We collected eye movement data from human subjects and built deep generative models of eye movements using a novel differentiable architecture for gaze fixations and gaze shifts. We found that human eye movements are best predicted by a model that is optimized not to perform the task as efficiently as possible but instead to run an internal simulation of an object traversing the maze. This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.

Topological data analysis (TDA) is an expanding field that leverages principles and tools from algebraic topology to quantify structural features of data sets or transform them into more manageable forms. As its theoretical foundations have been developed, TDA has shown promise in extracting useful information from high-dimensional, noisy, and complex data such as those used in biomedicine. To operate efficiently, these techniques may employ landmark samplers, either random or heuristic. The heuristic maxmin procedure obtains a roughly even distribution of sample points by implicitly constructing a cover comprising sets of uniform radius. However, issues arise with data that vary in density or include points with multiplicities, as are common in biomedicine. We propose an analogous procedure, "lastfirst" based on ranked distances, which implies a cover comprising sets of uniform cardinality. We first rigorously define the procedure and prove that it obtains landmarks with desired properties. We then perform benchmark tests and compare its performance to that of maxmin, on feature detection and class prediction tasks involving simulated and real-world biomedical data. Lastfirst is more general than maxmin in that it can be applied to any data on which arbitrary (and not necessarily symmetric) pairwise distances can be computed. Lastfirst is more computationally costly, but our implementation scales at the same rate as maxmin. We find that lastfirst achieves comparable performance on prediction tasks and outperforms maxmin on homology detection tasks. Where the numerical values of similarity measures are not meaningful, as in many biomedical contexts, lastfirst sampling may also improve interpretability.