基于梯度提升决策树（GBDT）的机器学习（ML）算法在从医疗保健到金融的各种任务关键应用程序中的许多表格数据任务上仍然受到青睐。但是，GBDT算法并不能免于偏见和歧视性决策的风险。尽管GBDT的受欢迎程度和公平ML研究的迅速发展，但现有的经过处理的公平ML方法要么不适用GBDT，因此在大量的火车时间内开销，或者由于高级失衡的问题而不足。我们提出FairgBM，这是一个在公平限制下培训GBDT的学习框架，与无约束的LightGBM相比，对预测性能几乎没有影响。由于常见的公平指标是不可差异的，因此我们使用平滑的凸错误率代理采用``代理 - 拉格朗日''公式来实现基于梯度的优化。此外，与相关工作相比，我们的开源实施在训练时间中显示了一个数量级的加速顺序，这是一个关键方面，旨在促进现实世界实践者对FairgBM的广泛采用。
translated by 谷歌翻译
近年来，机器学习算法在多种高风险决策应用程序中变得无处不在。机器学习算法从数据中学习模式的无与伦比的能力也使它们能够融合嵌入的偏差。然后，一个有偏见的模型可以做出不成比例地损害社会中某些群体的决策 - 例如，他们获得金融服务的机会。对这个问题的认识引起了公平ML领域，该领域的重点是研究，衡量和缓解算法预测的不公平性，相对于一组受保护的群体（例如种族或性别）。但是，算法不公平的根本原因仍然难以捉摸，研究人员在指责ML算法或训练的数据之间进行了划分。在这项工作中，我们坚持认为，算法不公平源于数据中模型与偏见之间的相互作用，而不是源于其中任何一个的孤立贡献。为此，我们提出了一种分类法来表征数据偏差，并研究了一系列关于公平盲目的ML算法在不同数据偏见设置下表现出的公平性准确性权衡的假设。在我们的现实帐户开放欺诈用例中，我们发现每个设置都需要特定的权衡，从而影响了预期价值和差异的公平性 - 后者通常没有注意到。此外，我们展示了算法在准确性和公平性方面如何根据影响数据的偏差进行比较。最后，我们注意到，在特定的数据偏见条件下，简单的预处理干预措施可以成功平衡小组错误率，而在更复杂的设置中相同的技术失败。
translated by 谷歌翻译
Code generation from text requires understanding the user's intent from a natural language description (NLD) and generating an executable program code snippet that satisfies this intent. While recent pretrained language models (PLMs) demonstrate remarkable performance for this task, these models fail when the given NLD is ambiguous due to the lack of enough specifications for generating a high-quality code snippet. In this work, we introduce a novel and more realistic setup for this task. We hypothesize that ambiguities in the specifications of an NLD are resolved by asking clarification questions (CQs). Therefore, we collect and introduce a new dataset named CodeClarQA containing NLD-Code pairs with created CQAs. We evaluate the performance of PLMs for code generation on our dataset. The empirical results support our hypothesis that clarifications result in more precise generated code, as shown by an improvement of 17.52 in BLEU, 12.72 in CodeBLEU, and 7.7\% in the exact match. Alongside this, our task and dataset introduce new challenges to the community, including when and what CQs should be asked.
translated by 谷歌翻译
Neural machine translation (NMT) has become the de-facto standard in real-world machine translation applications. However, NMT models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust. It becomes thus crucial to implement effective preventive strategies to guarantee their proper functioning. In this paper, we address the problem of hallucination detection in NMT by following a simple intuition: as hallucinations are detached from the source content, they exhibit encoder-decoder attention patterns that are statistically different from those of good quality translations. We frame this problem with an optimal transport formulation and propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model. Experimental results show that our detector not only outperforms all previous model-based detectors, but is also competitive with detectors that employ large models trained on millions of samples.
translated by 谷歌翻译
Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data -- which is prevalent in many high-stakes domains -- has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized,real-world bank account opening fraud detection dataset. This setting carries a set of challenges that are commonplace in real-world applications, including temporal dynamics and significant class imbalance. Additionally, to allow practitioners to stress test both performance and fairness of ML methods, each dataset variant of BAF contains specific types of data bias. With this resource, we aim to provide the research community with a more realistic, complete, and robust test bed to evaluate novel and existing methods.
translated by 谷歌翻译
2022-10-27
Current abstractive summarization systems present important weaknesses which prevent their deployment in real-world applications, such as the omission of relevant information and the generation of factual inconsistencies (also known as hallucinations). At the same time, automatic evaluation metrics such as CTC scores have been recently proposed that exhibit a higher correlation with human judgments than traditional lexical-overlap metrics such as ROUGE. In this work, we intend to close the loop by leveraging the recent advances in summarization metrics to create quality-aware abstractive summarizers. Namely, we propose an energy-based model that learns to re-rank summaries according to one or a combination of these metrics. We experiment using several metrics to train our energy-based re-ranker and show that it consistently improves the scores achieved by the predicted summaries. Nonetheless, human evaluation results show that the re-ranking approach should be used with care for highly abstractive summaries, as the available metrics are not yet sufficiently reliable for this purpose.
translated by 谷歌翻译
我们介绍了IST和Unmabel对WMT 2022关于质量估计（QE）的共享任务的共同贡献。我们的团队参与了所有三个子任务：（i）句子和单词级质量预测；（ii）可解释的量化宽松；（iii）关键错误检测。对于所有任务，我们在彗星框架之上构建，将其与OpenKIWI的预测估计架构连接，并为其配备单词级序列标记器和解释提取器。我们的结果表明，在预处理过程中合并参考可以改善下游任务上多种语言对的性能，并且通过句子和单词级别的目标共同培训可以进一步提高。此外，将注意力和梯度信息结合在一起被证明是提取句子级量化量化宽松模型的良好解释的首要策略。总体而言，我们的意见书在几乎所有语言对的所有三个任务中都取得了最佳的结果。
translated by 谷歌翻译
从有限的资源中获得最大收益可以进步自然语言处理（NLP）研究和实践，同时保守资源。这些资源可能是数据，时间，存储或能源。NLP的最新工作从缩放率产生了有趣的结果。但是，仅使用比例来改善结果意味着资源消耗也会扩展。这种关系激发了对有效方法的研究，这些方法需要更少的资源才能获得相似的结果。这项调查涉及NLP效率的方法和发现，旨在指导该领域的新研究人员并激发新方法的发展。
translated by 谷歌翻译
尽管神经机器翻译（NMT）中幻觉的问题受到了一些关注，但对这种高度病理现象的研究缺乏坚实的基础。以前的工作在几种方面受到限制：它通常诉诸于放大问题的人工环境，它无视一些（常见的）幻觉类型，并且不能验证检测启发式方法的充分性。在本文中，我们为研究NMT幻觉的研究设定了基础。首先，我们在自然环境中工作，即没有人造噪声的内域数据，既不在训练中也没有推理。接下来，我们注释一个超过3.4K句子的数据集，指示不同类型的关键错误和幻觉。然后，我们转向以前使用的检测方法和两种重新访问方法，并建议使用基于玻璃盒的不确定性检测器。总体而言，我们表明，对于预防性设置，（i）先前使用的方法在很大程度上不足，（ii）序列对数概要性效果最好，并且与基于参考的方法相同。最后，我们提出了脱足素剂，这是一种减轻测试时间的简单方法，可大大降低幻觉速度。为了简化未来的研究，我们发布了用于WMT18德语英语数据的注释数据集以及模型，培训数据和代码。
translated by 谷歌翻译
本文档描述了基于深度学习的点云几何编解码器和基于深度学习的点云关节几何和颜色编解码器，并提交给2022年1月发出的JPEG PLENO点云编码的建议。拟议的编解码器是基于最新的。基于深度学习的PC几何编码的发展，并提供了呼吁提案的一些关键功能。拟议的几何编解码器提供了一种压缩效率，可超过MPEG G-PCC标准和胜过MPEG的效率，或者与V-PCC Intra Intra Interra Interra Intra标准的竞争力均超过了jpeg呼叫提案测试集；但是，由于需要克服的质量饱和效应，关节几何和颜色编解码器不会发生同样的情况。
translated by 谷歌翻译