数据到文本(D2T)生成是从结构化输入生成文本的任务。我们观察到,当重复两次相同的目标句子时,基于变压器(T5)模型会产生由结构化输入的非对称句子组成的输出。换句话说,这些句子的长度和质量不同。我们称这种现象为“不对称产生”,并在D2T生成中利用了这一现象。生成不对称句子后,我们将使用无重复的目标添加输出的第一部分。随着渐进式编辑(PROEDIT)进行,召回增加。因此,此方法比在编辑之前更好地涵盖了结构化输入。证明是提高D2T生成性能的一种简单但有效的方法,它在Totto数据集中实现了新的状态结果
translated by 谷歌翻译
数据到文本生成系统旨在基于输入数据生成文本描述(通常以表格形式表示)。典型系统使用巨大的训练样本来学习表和文本之间的对应关系。然而,大型训练套装昂贵,可以获得这些方法在现实世界方案中的适用性。在这项工作中,我们专注于几次数据到文本生成。我们观察到,虽然微调预训练的语言模型可能会产生合理的句子,但它们在几次拍摄设置中遭受了低语义覆盖问题。换句话说,生成的文本中的重要输入时隙往往丢失。为此,我们提出了一种搜索和学习方法,可以利用预训练的语言模型,而是插入丢失的插槽以提高语义覆盖。我们根据搜索结果进一步微调我们的系统,以平滑搜索噪声,在很大程度上产生更好的质量文本并提高推理效率。实验表明,我们的模型在E2E和Wikibio数据集上实现了高性能。特别是,我们在E2E上覆盖了98.35%的输入槽,很大程度上减轻了低覆盖问题。
translated by 谷歌翻译
Large pre-trained language models have recently enabled open-ended generation frameworks (e.g., prompt-to-text NLG) to tackle a variety of tasks going beyond the traditional data-to-text generation. While this framework is more general, it is under-specified and often leads to a lack of controllability restricting their real-world usage. We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages. To address this task, we introduce a new dataset, called EntDeGen. Inspired by recent QA-based evaluation measures, we propose an automatic metric, MAFE, for factual correctness of generated descriptions. Our EntDescriptor model is equipped with strong rankers to fetch helpful passages and generate entity descriptions. Experimental result shows a good correlation (60.14) between our proposed metric and human judgments of factuality. Our rankers significantly improved the factual correctness of generated descriptions (15.95% and 34.51% relative gains in recall and precision). Finally, our ablation study highlights the benefit of combining keys and groundings.
translated by 谷歌翻译
维基百科是可理解知识的重要自由来源。尽管如此,巴西葡萄牙维基百科仍然缺乏对许多科目的描述。为了扩大巴西维基百科,我们贡献了Plsum,这是一种从多个描述性网站生成类似的Wiki的抽象摘要的框架。该框架具有提取阶段,然后是抽象。特别是,对于抽象阶段,我们微调并比较了变压器神经网络,PTT5和啰覆的最近最近的变化。为了微调和评估模型,我们创建了一个具有数千个示例的数据集,将参考网站链接到维基百科。我们的结果表明,可以从巴西葡萄牙语网上内容生成有意义的抽象摘要。
translated by 谷歌翻译
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.
translated by 谷歌翻译
拼写错误纠正是自然语言处理中具有很长历史的主题之一。虽然以前的研究取得了显着的结果,但仍然存在挑战。在越南语中,任务的最先进的方法从其相邻音节中介绍了一个音节的上下文。然而,该方法的准确性可能是不令人满意的,因为如果模型可能会失去上下文,如果两个(或更多)拼写错误彼此静置。在本文中,我们提出了一种纠正越南拼写错误的新方法。我们使用深入学习模型解决错误错误和拼写错误错误的问题。特别地,嵌入层由字节对编码技术提供支持。基于变压器架构的序列模型的序列使我们的方法与上一个问题不同于同一问题的方法。在实验中,我们用大型合成数据集训练模型,这是随机引入的拼写错误。我们使用现实数据集测试所提出的方法的性能。此数据集包含11,202个以9,341不同的越南句子中的人造拼写错误。实验结果表明,我们的方法达到了令人鼓舞的表现,检测到86.8%的误差,81.5%纠正,分别提高了最先进的方法5.6%和2.2%。
translated by 谷歌翻译
三重提取是自然语言处理和知识图构建信息提取的重要任务。在本文中,我们重新审视了序列生成的端到端三重提取任务。由于生成三重提取可能难以捕获长期依赖性并产生不忠的三元组,因此我们引入了一种新型模型,即与生成变压器的对比度三重提取。具体而言,我们为基于编码器的生成引入了一个共享的变压器模块。为了产生忠实的结果,我们提出了一个新颖的三胞胎对比训练对象。此外,我们引入了两种机制,以进一步提高模型性能(即,批处理动态注意力掩盖和三个方面的校准)。在三个数据集(即NYT,WebNLG和MIE)上进行的实验结果表明,我们的方法比基线的方法更好。
translated by 谷歌翻译
最近的工作表明,(1)增加输入长度或(2)增加模型大小可以提高基于变压器的神经模型的性能。在本文中,我们提出了一个名为Longt5的新模型,我们探讨了同时缩放输入长度和模型大小的效果。具体而言,我们综合了从长输入变压器(ETC)的关注思路,并采用了从摘要预训练(PEGASU)的预训练策略进入可扩展的T5架构。结果是我们称之为{\ EM瞬态全球}(TGLOBAL)的新关注机制,这些机制是模仿等本地/全球注意力机制,但不需要额外的侧面输入。我们能够实现最先进的结果,以若干摘要任务,优于问题应答任务的原始T5模型。
translated by 谷歌翻译
数据稀疏性是语法误差校正(GEC)的众所周知的问题。生成合成训练数据是针对此问题的一种广泛提出的解决方案,并允许模型近年来实现最新的(SOTA)性能。但是,这些方法通常会产生不切实际的错误,或者旨在仅一个错误生成句子。我们提出了一种基于学习的两个阶段方法,用于GEC的合成数据生成,从而放宽了仅包含一个错误的句子的约束。错误是根据句子优点产生的。我们表明,经过合成生成的语料库训练的GEC模型优于先前工作的合成数据的模型。
translated by 谷歌翻译
长文件摘要是自然语言处理领域的重要且艰巨的任务。良好的长文件摘要表现揭示了模型对人类语言的理解。目前,大多数研究侧重于如何修改变压器的注意机制,实现更高的胭脂分数。数据预处理和后处理的研究相对较少。在本文中,我们使用两个预处理方法和后处理方法,并分析了这些方法对各种长文件摘要模型的影响。
translated by 谷歌翻译
会话问题 - 转移生成是一项任务,它会自动生成一个基于输入段落的大规模对话问题回答数据集。在本文中,我们介绍了一个新颖的框架,该框架从一段段落中提取了值得问候的短语,然后在考虑以前的对话时产生相应的问题。特别是,我们的框架在生成问题后修改了提取的答案,以便答案与配对的问题完全匹配。实验结果表明,我们简单的答案修订方法可显着改善合成数据的质量。此外,我们证明我们的框架可以有效地用于域的适应会话问答。
translated by 谷歌翻译
State-of-the-art text simplification (TS) systems adopt end-to-end neural network models to directly generate the simplified version of the input text, and usually function as a blackbox. Moreover, TS is usually treated as an all-purpose generic task under the assumption of homogeneity, where the same simplification is suitable for all. In recent years, however, there has been increasing recognition of the need to adapt the simplification techniques to the specific needs of different target groups. In this work, we aim to advance current research on explainable and controllable TS in two ways: First, building on recently proposed work to increase the transparency of TS systems, we use a large set of (psycho-)linguistic features in combination with pre-trained language models to improve explainable complexity prediction. Second, based on the results of this preliminary task, we extend a state-of-the-art Seq2Seq TS model, ACCESS, to enable explicit control of ten attributes. The results of experiments show (1) that our approach improves the performance of state-of-the-art models for predicting explainable complexity and (2) that explicitly conditioning the Seq2Seq model on ten attributes leads to a significant improvement in performance in both within-domain and out-of-domain settings.
translated by 谷歌翻译
Text generation has made significant advances in the last few years. Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with human judgments. We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples. A key aspect of our approach is a novel pre-training scheme that uses millions of synthetic examples to help the model generalize. BLEURT provides state-ofthe-art results on the last three years of the WMT Metrics shared task and the WebNLG Competition dataset. In contrast to a vanilla BERT-based approach, it yields superior results even when the training data is scarce and out-of-distribution.
translated by 谷歌翻译
维基百科等文本知识库需要相当大的努力来保持最新和一致。虽然自动写作助手可能会缓解这一负担,但探讨了建议在外部知识基础上的建议的问题。在本文中,我们介绍了*忠实地反映了文本*(水果)中的更新信息的新颖一代任务是举办新证据的目标是更新现有文章。我们释放了Fruit-Wiki DataSet,一系列超过170k的远端监督数据,以及我们的数据生成管道和914个实例的金色评估集,其编辑被证据支持。我们为流行的发电系统以及编辑方法提供基准结果 - 根据编辑的基于T5的方法,我们介绍了确定现有技术的。我们的分析表明,开发可以忠实更新文章的开发模型需要新的神经发电模型的新功能,并打开更多新应用程序。
translated by 谷歌翻译
In this paper, we present strong baselines for the task of Feedback Comment Generation for Writing Learning. Given a sentence and an error span, the task is to generate a feedback comment explaining the error. Sentences and feedback comments are both in English. We experiment with LLMs and also create multiple pseudo datasets for the task, investigating how it affects the performance of our system. We present our results for the task along with extensive analysis of the generated comments with the aim of aiding future studies in feedback comment generation for English language learners.
translated by 谷歌翻译
本文介绍了一种自动评估对话系统中自然语言生成的自然。虽然这项任务以前通过昂贵且耗时的人类劳动力提供,但我们提出了这种新的生成语言自然评估的新任务。通过微调BERT模型,我们所提出的自然评估方法显示了稳健的结果,优于基线:支持向量机,双向LSTM和BLEurt。此外,通过从质量和信息性语言知识转移学习,改善了自然模型的训练速度和评估性能。
translated by 谷歌翻译
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.
translated by 谷歌翻译
生成的型号推理需要机器生成描述日常情景的句子,这是几种概念,最近引起了很多关注。然而,现有模型不能表现和人类,因为它们产生的句子通常是难以置疑和语法的不正确。在本文中,灵感来自人类创造句子的过程,我们提出了一种新颖的知识增强的致辞生成框架,被称为kgr ^ 4,由四个阶段组成:检索,回顾,精炼,重新思考。在此框架下,我们首先执行检索以搜索从外部语料库作为原型的相关句子。然后,我们训练发电机编辑或复制这些原型以生成候选句子,其中基于AutoEncoder的炼油器将修复候选句子。最后,我们从具有不同超参数的生成器产生的候选句子中选择输出句子。对蒙古基准测试的实验结果和深入分析强烈展示了我们框架的有效性。特别是,KGR ^ 4获得官方排行榜中的33.56个香料点,优于前面报告的最佳结果2.49香料点,实现最先进的性能。
translated by 谷歌翻译
非自动回旋(NAR)模型的计算能力比自回归模型较少,但牺牲生成质量可以生成句子。先前的研究通过迭代解码解决了这个问题。这项研究建议将最近的邻居用作NAR解码器的初始状态,并迭代编辑。我们提出了一种新颖的培训策略,以了解有关邻居的编辑操作,以改善NAR文本生成。实验结果表明,所提出的方法(邻域)在JRC-ACQUISIE EN-DE DATASET上获得了更高的翻译质量(比香草变压器高1.69点(比香草变压器高1.69点),而解码迭代率较少(少于十分之一)使用最近的邻居翻译。我们还确认了所提出的方法对数据到文本任务(Wikibio)的有效性。此外,所提出的方法在WMT'14 EN-DE数据集上优于NAR基线。我们还报告了建议方法中使用的邻居示例的分析。
translated by 谷歌翻译
具有复制机制的最近神经序列到序列模型在各种文本生成任务中取得了显着的进展。这些模型解决了词汇问题,并促进了稀有词的产生。然而,如先前的复制模型所观察到的,难以产生的,难以产生和缺乏抽象,难以识别。在本文中,我们提出了一种副本网络的新颖监督方法,该方法可帮助模型决定需要复制哪些单词并需要生成。具体而言,我们重新定义目标函数,它利用源序列和目标词汇表作为复制的指导。关于数据到文本生成和抽象总结任务的实验结果验证了我们的方法提高了复制质量,提高了抽象程度。
translated by 谷歌翻译