End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called 'likelihood trap', resulting in generated responses which are dull, repetitive, and often inconsistent with dialogue history. Comparing ranked lists of multiple generated responses against the 'gold response' (from training data) reveals a wide diversity in response quality, with many good responses placed lower in the ranked list. The main challenge, addressed in this work, is then how to reach beyond greedily generated system responses, that is, how to obtain and select such high-quality responses from the list of overgenerated responses at inference without availability of the gold response. To this end, we propose a simple yet effective reranking method which aims to select high-quality items from the lists of responses initially overgenerated by the system. The idea is to use any sequence-level (similarity) scoring function to divide the semantic space of responses into high-scoring versus low-scoring partitions. At training, the high-scoring partition comprises all generated responses whose similarity to the gold response is higher than the similarity of the greedy response to the gold response. At inference, the aim is to estimate the probability that each overgenerated response belongs to the high-scoring partition, given only previous dialogue history. We validate the robustness and versatility of our proposed method on the standard MultiWOZ dataset: our methods improve a state-of-the-art E2E ToD system by 2.4 BLEU, 3.2 ROUGE, and 2.8 METEOR scores, achieving new peak results. Additional experiments on the BiTOD dataset and human evaluation further ascertain the generalisability and effectiveness of the proposed framework.

学习高质量的对话表示对于解决各种面向对话的任务至关重要，尤其是考虑到对话系统通常会遇到数据稀缺。在本文中，我们介绍了对话句子嵌入（DSE），这是一种自我监督的对比学习方法，它学习有效的对话表示，适合各种对话任务。 DSE通过连续进行与对比度学习的正面对话的连续对话来从对话中学习。尽管它很简单，但DSE的表现能力比其他对话表示和普遍的句子表示模型要好得多。我们评估DSE的五个下游对话任务，这些任务检查了不同语义粒度的对话表示。几次射击和零射击设置的实验表明，DSE的表现要优于基线。例如，它在6个数据集中的1-Shot意图分类中比最强的无监督基线实现了13％的平均绩效提高。我们还提供了有关模型的好处和局限性的分析。

基于检索的对话响应选择旨在为给定多转中下文找到候选集的正确响应。基于预先训练的语言模型（PLMS）的方法对此任务产生了显着的改进。序列表示在对话背景和响应之间的匹配程度中扮演关键作用。然而，我们观察到相同上下文共享的不同的上下文响应对始终在由PLM计算的序列表示中具有更大的相似性，这使得难以区分来自负面的正响应。由此激励，我们提出了一种基于PLMS的响应选择任务的新颖\ TextBF {f} ine- \ textbf {g}下载\ textbf {g} unfrstive（fgc）学习方法。该FGC学习策略有助于PLMS在细粒中产生每个对话的更可区分的匹配表示，并进一步提高选择正反应的预测。两个基准数据集的实证研究表明，所提出的FGC学习方法一般可以提高现有PLM匹配模型的模型性能。

我们介绍了AARGH，这是一个面向任务的对话框系统，该系统结合了单个模型中的检索和生成方法，旨在改善对话框管理和输出的词汇多样性。该模型采用了一种新的响应选择方法，该方法基于动作感知训练目标和简化的单编码检索架构，该方法使我们能够构建端到端检索增强生成模型，在该模型中，检索和生成共享大多数参数。在Multiwoz数据集上，我们表明我们的方法与最先进的基线相比，在维持或改善状态跟踪和上下文响应生成性能的同时，产生了更多的输出。

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always rely on auto-regressive decoding. However, previous methods using contrastive learning in neural text generation usually lead to inferior performance. In this paper, we analyse the underlying reasons and propose a new Contrastive Neural Text generation framework, CoNT. CoNT addresses bottlenecks that prevent contrastive learning from being widely adopted in generation tasks from three aspects -- the construction of contrastive examples, the choice of the contrastive loss, and the strategy in decoding. We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation. Experimental results show that CoNT clearly outperforms the conventional training framework on all the ten benchmarks with a convincing margin. Especially, CoNT surpasses previous the most competitive contrastive learning method for text generation, by 1.50 BLEU on machine translation and 1.77 ROUGE-1 on summarization, respectively. It achieves new state-of-the-art on summarization, code comment generation (without external data) and data-to-text generation.

The goal of building dialogue agents that can converse with humans naturally has been a long-standing dream of researchers since the early days of artificial intelligence. The well-known Turing Test proposed to judge the ultimate validity of an artificial intelligence agent on the indistinguishability of its dialogues from humans'. It should come as no surprise that human-level dialogue systems are very challenging to build. But, while early effort on rule-based systems found limited success, the emergence of deep learning enabled great advance on this topic. In this thesis, we focus on methods that address the numerous issues that have been imposing the gap between artificial conversational agents and human-level interlocutors. These methods were proposed and experimented with in ways that were inspired by general state-of-the-art AI methodologies. But they also targeted the characteristics that dialogue systems possess.

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking statements that are irrelevant or factually incorrect. To address this problem, we propose a contrastive learning scheme, named MixCL. A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs, and thus reduce their hallucination in conversations. We also examine negative sampling strategies of retrieved hard negatives and model-generated negatives. We conduct experiments on Wizard-of-Wikipedia, a public, open-domain knowledge-grounded dialogue benchmark, and assess the effectiveness of MixCL. MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality. We show that MixCL achieves comparable performance to state-of-the-art KB-based approaches while enjoying notable advantages in terms of efficiency and scalability.

Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that are more natural and better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the lower level of interpretability of deep neural networks, the controllability of these methods need to be guaranteed. To this end, controllable text generation using transformer-based PLMs has become a rapidly growing yet challenging new research hotspot. A diverse range of approaches have emerged in the recent 3-4 years, targeting different CTG tasks which may require different types of controlled constraints. In this paper, we present a systematic critical review on the common tasks, main approaches and evaluation methods in this area. Finally, we discuss the challenges that the field is facing, and put forward various promising future directions. To the best of our knowledge, this is the first survey paper to summarize CTG techniques from the perspective of PLMs. We hope it can help researchers in related fields to quickly track the academic frontier, providing them with a landscape of the area and a roadmap for future research.

Personalized chatbots focus on endowing the chatbots with a consistent personality to behave like real users and further act as personal assistants. Previous studies have explored generating implicit user profiles from the user's dialogue history for building personalized chatbots. However, these studies only use the response generation loss to train the entire model, thus it is prone to suffer from the problem of data sparsity. Besides, they overemphasize the final generated response's quality while ignoring the correlations and fusions between the user's dialogue history, leading to rough data representations and performance degradation. To tackle these problems, we propose a self-supervised learning framework MCP for capturing better representations from users' dialogue history for personalized chatbots. Specifically, we apply contrastive sampling methods to leverage the supervised signals hidden in user dialog history, and generate the pre-training samples for enhancing the model. We design three pre-training tasks based on three types of contrastive pairs from user dialogue history, namely response pairs, sequence augmentation pairs, and user pairs. We pre-train the utterance encoder and the history encoder towards the contrastive objectives and use these pre-trained encoders for generating user profiles while personalized response generation. Experimental results on two real-world datasets show a significant improvement in our proposed model MCP compared with the existing methods.

Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.

Crosstalk是一种传统的中国戏剧表演艺术。它通常由两个表演者以对话的形式执行。凭借对话的典型特征，串扰也被设计为有趣的观众。在这项研究中，我们介绍了Crossdial，这是第一个开源数据集，其中包含来自网络上最经典的中国串扰。此外，我们定义了两个新任务，提供了两个基准，并研究了当前的对话生成模型在串扰生成领域的能力。实验结果和案例研究表明，串扰的生成对于直接方法来说是具有挑战性的，并且仍然是未来工作的有趣主题。

在本文中，我们建议利用对话的独特特征，共享参与者的常识性知识，以解决总结它们的困难。我们提出了病态的框架，该框架使用常识推论作为其他背景。与以前仅依赖于输入对话的工作相比，Sick使用外部知识模型来生成丰富的常识推断，并选择具有基于相似性选择方法的最可能的推理。基于生病的，病人++的理解为监督，在总结多任务学习环境中的对话时，添加了产生常识推断的任务。实验结果表明，通过注入常识性知识，我们的框架比现有方法产生更多信息和一致的摘要。

文本生成对于许多自然语言处理应用至关重要。然而，基于最大化的解码方法（例如，神经语言模型的光束搜索）通常会导致解析解决方案 - 生成的文本是不自然的，并且包含不良的重复。现有方法通过采样或修改训练目标引入随机性，以降低某些令牌的概率（例如，不可能训练）。但是，它们通常会导致缺乏连贯性的解决方案。在这项工作中，我们表明，模型变性的根本原因是令牌表示的各向异性分布。我们提出了一种对比解决方案：（i）SIMCTG，是校准模型表示空间的对比训练目标，以及（ii）一种解码方法 - 对比度搜索 - 以鼓励多样性，同时在生成的文本中保持连贯性。对两种语言的三个基准测试的广泛实验和分析表明，我们提出的方法显着优于人类和自动指标评估的当前最新文本生成方法。

Pre-trained language models have been successful in natural language generation (NLG) tasks. While various decoding methods have been employed, they often produce suboptimal results. We first present an empirical analysis of three NLG tasks: summarization, machine translation, and constrained text generation. We found that selecting the best output from the results of multiple decoding methods can significantly improve performance. To further improve reranking for NLG tasks, we proposed a novel method, \textsc{PairReranker}, which uses a single encoder and a pairwise loss function to jointly encode a source input and a pair of candidates and compare them. Experiments on three NLG tasks demonstrated the effectiveness and flexibility of \textsc{PairReranker}, showing strong results, compared with previous baselines. In addition, our \textsc{PairReranker} can generalize to significantly improve GPT-3 (text-davinci-003) results (e.g., 24.55\% on CommonGen and 11.35\% on WMT18 zh-en), even though our rerankers are not trained with any GPT-3 candidates.

预先接受的语言模型（PLM）在神经对话建模中标志着巨大的飞跃。虽然PLMS在大型文本语料库上进行预先培训，但通常在具有特定领域知识和对话风格的稀缺对话数据上进行微调。然而，在大型预先训练模型中充分利用现有知识的同时定制语言模型仍然是一个挑战。在本文中，我们提出了一种预先接受训练的对话建模的新方法，将对话生成问题作为一个快速学习任务。而不是在有限的对话数据上进行微调，我们的方法，DialogPrompt学习针对对话背景优化的连续提示嵌入，从而从大型预训练模型中促进了知识。为了鼓励模型更好地利用提示嵌入，提示编码器被设计为在输入对话框上下文中的条件。流行对话数据集的实验表明，我们的方法显着优于微调基线和通用及时学习方法。此外，人类评估强烈支持对DialialPrompt的优越性在响应生成质量方面。

这项工作结合了有关预先训练模型编码的对话历史的信息，其含义表示当前系统话语，以实现面向任务对话中的语境语言生成。我们利用预先训练的多上下文转换模型进行从头开始培训的模型中的上下文表示;并利用从预训练的GPT-2调整的模型中的上下文生成的立即使用前面的用户话语。与多种数据集的两个实验表明，通过预先训练的模型编码的上下文信息可提高自动指标和人类评估中的响应生成的性能。我们所呈现的上下文发电机使得更高种类的响应能够更好地适应正在进行的对话。分析上下文大小显示，较长的上下文不会自动导致更好的性能，但是前面的用户话语的直接对上下文生成起着重要作用。此外，我们还提出了一种基于GPT的生成模型的重新排名。实验表明，RE-Ranker选择的响应对自动度量有重大改进。

用于提取和抽象性摘要系统的传统培训范例始终仅使用令牌级别或句子级培训目标。但是，始终从摘要级别评估输出摘要，从而导致培训和评估的不一致。在本文中，我们提出了一个基于对比度学习的重新排列框架，用于一阶段的摘要，称为COLO。通过建模对比目标，我们表明摘要模型能够根据摘要级别的分数直接生成摘要，而无需其他模块和参数。广泛的实验表明，CORO在CNN/DailyMail基准测试中提高了单阶段系统的提取和抽象结果，将其提高到44.58和46.33 Rouge-1得分，同时保留了参数效率和推断效率。与最先进的多阶段系统相比，我们节省了100多个GPU训练时间，并在推理期间获得3〜8加速比，同时保持可比的结果。

由于暴露偏见，大多数现有的自然语言产生（NLG）模型通过最大化的可能性目标训练了推理阶段的文本结果不佳。在本文中，为了解决此问题，我们重新审视生成的框架，并提出了用于文本生成任务的联合发电机库（JGR）培训算法。在JGR中，生成器模型是通过最大化两个目标来训练的：训练语料库的可能性和排名者模型给出的预期奖励。同时，Ranker模型从发电机模型中获取输入样本，并学会了将优质样本与生成池区分开来。发电机和排名模型交替优化，直到收敛为止。在实证研究中，提出的JGR模型在五个公共基准测试中实现了新的最先进的表现，涵盖了三项大众一代任务：摘要，问题生成和回答生成。我们将在https://github.com/microsoft/advnlg上提供代码，数据和模型。

Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. This calls for a dedicated network architecture for domain generalization. To tackle the multi-domain dialogue evaluation task, we propose a Panel of Experts (PoE), a multitask network that consists of a shared transformer encoder and a collection of lightweight adapters. The shared encoder captures the general knowledge of dialogues across domains, while each adapter specializes in one specific domain and serves as a domain expert. To validate the idea, we construct a high-quality multi-domain dialogue dataset leveraging data augmentation and pseudo-labeling. The PoE network is comprehensively assessed on 16 dialogue evaluation datasets spanning a wide range of dialogue domains. It achieves state-of-the-art performance in terms of mean Spearman correlation over all the evaluation datasets. It exhibits better zero-shot generalization than existing state-of-the-art ADEMs and the ability to easily adapt to new domains with few-shot transfer learning.

We propose BERTSCORE, an automatic evaluation metric for text generation. Analogously to common metrics, BERTSCORE computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTSCORE correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTSCORE is more robust to challenging examples when compared to existing metrics.