Functionality and dialogue experience are two important factors of task-oriented dialogue systems. Conventional approaches with closed schema (e.g., conversational semantic parsing) often fail as both the functionality and dialogue experience are strongly constrained by the underlying schema. We introduce a new paradigm for task-oriented dialogue - Dialog2API - to greatly expand the functionality and provide seamless dialogue experience. The conversational model interacts with the environment by generating and executing programs triggering a set of pre-defined APIs. The model also manages the dialogue policy and interact with the user through generating appropriate natural language responses. By allowing generating free-form programs, Dialog2API supports composite goals by combining different APIs, whereas unrestricted program revision provides natural and robust dialogue experience. To facilitate Dialog2API, the core model is provided with API documents, an execution environment and optionally some example dialogues annotated with programs. We propose an approach tailored for the Dialog2API, where the dialogue states are represented by a stack of programs, with most recently mentioned program on the top of the stack. Dialog2API can work with many application scenarios such as software automation and customer service. In this paper, we construct a dataset for AWS S3 APIs and present evaluation results of in-context learning baselines.

Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks. ARCADE features multiple rounds of NL-to-code problems from the same notebook. It requires a model to understand rich multi-modal contexts, such as existing notebook cells and their execution states as well as previous turns of interaction. To establish a strong baseline on this challenging task, we develop PaChiNCo, a 62B code language model (LM) for Python computational notebooks, which significantly outperforms public code LMs. Finally, we explore few-shot prompting strategies to elicit better code with step-by-step decomposition and NL explanation, showing the potential to improve the diversity and explainability of model predictions.

Semantic Machines (SM) have introduced the use of the dataflow (DF) paradigm to dialogue modelling, using computational graphs to hierarchically represent user requests, data, and the dialogue history [Semantic Machines et al. 2020]. Although the main focus of that paper was the SMCalFlow dataset (to date, the only dataset with "native" DF annotations), they also reported some results of an experiment using a transformed version of the commonly used MultiWOZ dataset [Budzianowski et al. 2018] into a DF format. In this paper, we expand the experiments using DF for the MultiWOZ dataset, exploring some additional experimental set-ups. The code and instructions to reproduce the experiments reported here have been released. The contributions of this paper are: 1.) A DF implementation capable of executing MultiWOZ dialogues; 2.) Several versions of conversion of MultiWOZ into a DF format are presented; 3.) Experimental results on state match and translation accuracy.

Task-oriented semantic parsing is increasingly being used in user-facing applications, making measuring the calibration of parsing models especially important. We examine the calibration characteristics of six models across three model families on two common English semantic parsing datasets, finding that many models are reasonably well-calibrated and that there is a trade-off between calibration and performance. Based on confidence scores across three models, we propose and release new challenge splits of the two datasets we examine. We then illustrate the ways a calibrated model can be useful in balancing common trade-offs in task-oriented parsing. In a simulated annotator-in-the-loop experiment, we show that using model confidence allows us to improve the accuracy on validation programs by 9.6% (absolute) with annotator interactions on only 2.2% of tokens. Using sequence-level confidence scores, we then examine how we can optimize trade-off between a parser's usability and safety. We show that confidence-based thresholding can reduce the number of incorrect low-confidence programs executed by 76%; however, this comes at a cost to usability. We propose the DidYouMean system which balances usability and safety. We conclude by calling for calibration to be included in the evaluation of semantic parsing systems, and release a library for computing calibration metrics.

大型语言模型，例如OpenAI的法典和DeepMind的字母，可以生成代码来解决以自然语言表达的各种问题。这项技术已经在至少一项广泛使用的编程编辑器扩展程序中进行了商业化：Github Copilot。在本文中，我们探讨了具有大型语言模型（LLM辅助编程）的编程与程序员协助的先前概念化相似，并且与众不同。我们借鉴了公开可用的经验报告，有关LLM辅助编程以及先前的可用性和设计研究。我们发现，尽管LLM辅助编程通过搜索和重用分享了一些编译，配对编程和编程的属性，但技术可能性和实践经验都存在根本差异。因此，应该将LLM辅助编程视为具有自己独特的属性和挑战的新方法。最后，我们借鉴了用户研究的观察结果，在该观察中，非专家最终用户程序员使用LLM辅助工具来求解电子表格中的数据任务。我们讨论可能出现的问题，并在将大型语言模型应用于最终用户编程时，尤其是对于几乎没有编程专业知识的用户。

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。

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。

We propose AnyTOD, an end-to-end task-oriented dialog (TOD) system with zero-shot capability for unseen tasks. We view TOD as a program executed by a language model (LM), where program logic and ontology is provided by a designer in the form of a schema. To enable generalization onto unseen schemas and programs without prior training, AnyTOD adopts a neuro-symbolic approach. A neural LM keeps track of events that occur during a conversation, and a symbolic program implementing the dialog policy is executed to recommend next actions AnyTOD should take. This approach drastically reduces data annotation and model training requirements, addressing a long-standing challenge in TOD research: rapidly adapting a TOD system to unseen tasks and domains. We demonstrate state-of-the-art results on the STAR and ABCD benchmarks, as well as AnyTOD's strong zero-shot transfer capability in low-resource settings. In addition, we release STARv2, an updated version of the STAR dataset with richer data annotations, for benchmarking zero-shot end-to-end TOD models.

Task-oriented dialogue (TOD) systems are mainly based on the slot-filling-based TOD (SF-TOD) framework, in which dialogues are broken down into smaller, controllable units (i.e., slots) to fulfill a specific task. A series of approaches based on this framework achieved remarkable success on various TOD benchmarks. However, we argue that the current TOD benchmarks are limited to surrogate real-world scenarios and that the current TOD models are still a long way from unraveling the scenarios. In this position paper, we first identify current status and limitations of SF-TOD systems. After that, we explore the WebTOD framework, the alternative direction for building a scalable TOD system when a web/mobile interface is available. In WebTOD, the dialogue system learns how to understand the web/mobile interface that the human agent interacts with, powered by a large-scale language model.

用户模拟器（USS）通常用于通过增强学习训练面向任务的对话系统（DSS）。相互作用通常是在语义层面上以提高效率的，但是从语义动作到自然语言仍然存在差距，这会导致培训和部署环境之间的不匹配。在培训期间，将自然语言生成（NLG）模块与USS结合在一起可以部分解决此问题。但是，由于US的策略和NLG是单独优化的，因此在给定的情况下，这些模拟的用户话语可能不够自然。在这项工作中，我们提出了一个基于生成变压器的用户模拟器（Gentus）。 Gentus由编码器结构组成，这意味着它可以共同优化用户策略和自然语言。 Gentus既产生语义动作又产生自然语言话语，从而保留了解释性和增强语言的变化。另外，通过将输入和输出表示为单词序列以及使用大型的预训练语言模型，我们可以在功能表示中实现普遍性。我们通过自动指标和人类评估评估绅士。我们的结果表明，绅士会产生更多的自然语言，并能够以零拍的方式转移到看不见的本体论中。此外，通过加强学习为培训专业用户模拟器打开大门，可以进一步塑造其行为。

在最近的工作中已显示出一种模式指导的对话管理方法，可以有效地创建能够充当友好同行或任务助理的强大定制虚拟代理。但是，这些方法在开放式，混合初始性领域中的成功应用仍然难以捉摸 - 尤其是在诸如虚拟标准化患者之类的医疗领域，在这种复杂的互动很常见的情况下 - 比以前的系统需要更广泛，更灵活的对话管理能力提供。在本文中，我们描述了用于开发索菲（Sophie）的通用架构指导的对话管理框架，Sophie是一种虚拟标准化的癌症患者，可让医生方便地练习与患者的互动。我们对医学生和索菲之间的对话进行了众包评估。我们的经纪人被认为是自然，情感上适当的反应，并且与她作为癌症患者的角色一致。此外，它大大优于对人类标准化患者语料库进行微调的端到端神经模型，这证明了模式引导方法的优势。

在人类空间中运营的机器人必须能够与人的自然语言互动，既有理解和执行指示，也可以使用对话来解决歧义并从错误中恢复。为此，我们介绍了教学，一个超过3,000人的互动对话的数据集，以完成模拟中的家庭任务。一个有关任务的Oracle信息的指挥官以自然语言与追随者通信。追随者通过环境导航并与环境进行互动，以完成从“咖啡”到“准备早餐”的复杂性不同的任务，提出问题并从指挥官获取其他信息。我们提出三个基准使用教学研究体现了智能挑战，我们评估了对话理解，语言接地和任务执行中的初始模型的能力。

我们提出了Blenderbot 3，这是一个175B参数对话模型，能够通过访问Internet和长期内存进行开放域对话，并接受了大量用户定义的任务的培训。我们同时发布了模型权重和代码，还将模型部署在公共网页上，以与有机用户进行交互。该技术报告描述了该模型的构建方式（建筑，模型和培训计划）以及其部署的细节，包括安全机制。人类评估表明，它优于现有的开放域对话代理，包括其前身（Roller等，2021； Komeili等，2022）。最后，我们使用部署收集的数据详细介绍了持续学习的计划，该数据也将公开发布。因此，该研究计划的目标是使社区能够研究通过互动学习的不断改进的负责任的代理商。

Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction, but the main LM benchmarks are non-interactive, where a system produces output without human intervention. To evaluate human-LM interaction, we develop a framework, Human-AI Language-based Interaction Evaluation (H-LINE), that expands non-interactive evaluation along three dimensions, capturing (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality. We then design five tasks ranging from goal-oriented to open-ended to capture different forms of interaction. On four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21's J1-Jumbo), we find that non-interactive performance does not always result in better human-LM interaction and that first-person and third-party metrics can diverge, suggesting the importance of examining the nuances of human-LM interaction.

Virtual assistants such as Google Assistant, Alexa and Siri provide a conversational interface to a large number of services and APIs spanning multiple domains. Such systems need to support an ever-increasing number of services with possibly overlapping functionality. Furthermore, some of these services have little to no training data available. Existing public datasets for task-oriented dialogue do not sufficiently capture these challenges since they cover few domains and assume a single static ontology per domain. In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains. Our dataset exceeds the existing task-oriented dialogue corpora in scale, while also highlighting the challenges associated with building large-scale virtual assistants. It provides a challenging testbed for a number of tasks including language understanding, slot filling, dialogue state tracking and response generation. Along the same lines, we present a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots, provided as input, using their natural language descriptions. This allows a single dialogue system to easily support a large number of services and facilitates simple integration of new services without requiring additional training data. Building upon the proposed paradigm, we release a model for dialogue state tracking capable of zero-shot generalization to new APIs, while remaining competitive in the regular setting.

这项工作提出了一个新的对话数据集，即cookdial，该数据集促进了对任务知识了解的面向任务的对话系统的研究。该语料库包含260个以人类对任务为导向的对话框，其中代理给出了配方文档，指导用户烹饪菜肴。 Cookdial中的对话框展示了两个独特的功能：（i）对话流与支持文档之间的程序对齐； （ii）复杂的代理决策涉及分割长句子，解释硬说明并在对话框上下文中解决核心。此外，我们在假定的面向任务的对话框系统中确定了三个具有挑战性的（子）任务：（1）用户问题理解，（2）代理操作框架预测和（3）代理响应生成。对于这些任务中的每一个，我们都会开发一个神经基线模型，我们在cookdial数据集上进行了评估。我们公开发布烹饪数据集，包括对话框和食谱文档的丰富注释，以刺激对特定于域的文档接地对话框系统的进一步研究。

以任务为导向的对话系统（TDSS）主要在离线设置或人类评估中评估。评估通常仅限于单转或非常耗时。作为替代方案，模拟用户行为的用户模拟器使我们能够考虑一组广泛的用户目标，以生成类似人类的对话以进行模拟评估。使用现有的用户模拟器来评估TDSS是具有挑战性的，因为用户模拟器主要旨在优化TDSS的对话策略，并且评估功能有限。此外，对用户模拟器的评估是一个开放的挑战。在这项工作中，我们提出了一个用于端到端TDS评估的隐喻用户模拟器，如果它在与系统的交互中模拟用户的类似思维，则定义模拟器是隐喻的。我们还提出了一个基于测试人员的评估框架，以生成变体，即具有不同功能的对话系统。我们的用户模拟器构建了一个隐喻的用户模型，该模型通过参考遇到新项目时的先验知识来帮助模拟器进行推理。我们通过检查模拟器与变体之间的模拟相互作用来估计模拟器的质量。我们的实验是使用三个TDS数据集进行的。与基于议程的模拟器和三个数据集上的SEQ2SEQ模型相比，隐喻用户模拟器与手动评估的一致性更好。我们的测试人员框架展示了效率，并且可以更好地概括和可扩展性，因为它可以适用于多个域中的对话和多个任务，例如对话建议和电子商务对话。

我们提出了一个开放域的社交聊天机器人Chirpy Cardinal。为了既有信息又有信息，我们的机器人以一种真实的，情感上的方式与用户聊天。通过将受控的神经产生与脚手架，手写的对话整合在一起，我们让用户和机器人都轮流推动对话，从而产生引人入胜且流利的体验。Chirpy Cardinal部署在Alexa奖Socialbot Grand Challenge的第四次迭代中，每天处理数千次对话，在9个机器人中排名第二，平均用户评级为3.58/5。

如何有效地构建和使用对话数据，以及如何在不同域中在不同域中部署模型可能是建立面向任务的对话系统的两个关键问题。在本文中，我们提出了一种新颖的手动指导对话方案，以减轻这些问题，在该方案中，代理商从对话和手册中学习任务。该手册是一个非结构化的文本文档，可指导代理在对话过程中与用户和数据库进行交互。我们提出的方案降低了对话模型对细粒领域本体的依赖性，并使它们更灵活以适应各种领域。然后，我们为完全注销的多域数据集Magdial贡献以支持我们的方案。它介绍了三个对话建模子任务：指令匹配，参数填充和响应生成。对这些子任务进行建模与人类代理的行为模式一致。实验表明，手动引导对话方案提高了构建对话系统中的数据效率和域可伸缩性。数据集和基准将公开用于促进未来的研究。

我们提出了Tacobot，这是为首届Alexa Prive Taskbot Challenge构建的面向任务的对话系统，该系统可帮助用户完成多步骤烹饪和家庭装修任务。Tacobot的设计采用以用户为中心的原则，并渴望提供协作且易于访问的对话体验。为此，它具有准确的语言理解，灵活的对话管理和引人入胜的响应生成。此外，Tacobot还以强大的搜索引擎和自动化的端到端测试套件为支持。在引导Tacobot的开发中，我们探索了一系列数据增强策略，以训练先进的神经语言处理模型，并通过收集的真实对话不断改善对话经验。在半决赛结束时，Tacobot的平均评分为3.55/5.0。