徽标检索是一个具有挑战性的问题,因为与图像检索任务相比,相似性的定义更为主观,并且已知相似性的集合非常稀缺。为了应对这一挑战,在本文中,我们提出了一种简单但有效的基于细分市场的增强策略,以引入人工相似的徽标,以训练徽标检索的深层网络。在这种新颖的增强策略中,我们首先在徽标中找到细分市场,并在细分市场上应用旋转,缩放和颜色变化等转换,这与传统的图像级增强策略不同。此外,我们评估最近引入的基于排名的损失函数Smooth-AP是否是学习徽标检索相似性的更好方法。在大规模的METU商标数据集上,我们表明(i)基于细分市场的增强策略与基线模型或图像级增强策略相比提高了检索性能,并且(ii)平滑 - AP的表现确实比徽标的常规损失更好恢复。
translated by 谷歌翻译
Dense retrievers have made significant strides in obtaining state-of-the-art results on text retrieval and open-domain question answering (ODQA). Yet most of these achievements were made possible with the help of large annotated datasets, unsupervised learning for dense retrieval models remains an open problem. In this work, we explore two categories of methods for creating pseudo query-document pairs, named query extraction (QExt) and transferred query generation (TQGen), to augment the retriever training in an annotation-free and scalable manner. Specifically, QExt extracts pseudo queries by document structures or selecting salient random spans, and TQGen utilizes generation models trained for other NLP tasks (e.g., summarization) to produce pseudo queries. Extensive experiments show that dense retrievers trained with individual augmentation methods can perform comparably well with multiple strong baselines, and combining them leads to further improvements, achieving state-of-the-art performance of unsupervised dense retrieval on both BEIR and ODQA datasets.
translated by 谷歌翻译
Parsing natural language questions into executable logical forms is a useful and interpretable way to perform question answering on structured data such as knowledge bases (KB) or databases (DB). However, existing approaches on semantic parsing cannot adapt to both modalities, as they suffer from the exponential growth of the logical form candidates and can hardly generalize to unseen data. In this work, we propose Uni-Parser, a unified semantic parser for question answering (QA) on both KB and DB. We introduce the primitive (relation and entity in KB, and table name, column name and cell value in DB) as an essential element in our framework. The number of primitives grows linearly with the number of retrieved relations in KB and DB, preventing us from dealing with exponential logic form candidates. We leverage the generator to predict final logical forms by altering and composing topranked primitives with different operations (e.g. select, where, count). With sufficiently pruned search space by a contrastive primitive ranker, the generator is empowered to capture the composition of primitives enhancing its generalization ability. We achieve competitive results on multiple KB and DB QA benchmarks more efficiently, especially in the compositional and zero-shot settings.
translated by 谷歌翻译
We propose a) a Language Agnostic end-to-end Speech Translation model (LAST), and b) a data augmentation strategy to increase code-switching (CS) performance. With increasing globalization, multiple languages are increasingly used interchangeably during fluent speech. Such CS complicates traditional speech recognition and translation, as we must recognize which language was spoken first and then apply a language-dependent recognizer and subsequent translation component to generate the desired target language output. Such a pipeline introduces latency and errors. In this paper, we eliminate the need for that, by treating speech recognition and translation as one unified end-to-end speech translation problem. By training LAST with both input languages, we decode speech into one target language, regardless of the input language. LAST delivers comparable recognition and speech translation accuracy in monolingual usage, while reducing latency and error rate considerably when CS is observed.
translated by 谷歌翻译
在本文中,我们将概述SV形式共享任务,作为第三届学术文档处理(SDP)的一部分,在Coling 2022.中,在共同的任务中,为参与者提供了变量和变量的词汇,被要求确定全文学术文档中的单个句子中提到了哪些变量。两支球队总共向共享任务排行榜提交了9项意见。尽管所有团队都没有改进基线系统,但我们仍然从他们的意见书中获取见解。此外,我们提供了详细的评估。我们共享任务的数据和基线可在https://github.com/vadis-project/sv-inend上免费获得
translated by 谷歌翻译
变压器体系结构在许多最新应用程序中取得了显着进展。然而,尽管他们取得了成功,但现代变形金刚依赖于自我发挥的机制,其时间和空间复杂性在输入的长度上是二次的。已经提出了几种方法来加快自我注意力的机制以实现次级运行时间。但是,这些作品中的绝大多数并不伴随着严格的错误保证。在这项工作中,我们在许多情况下就自我注意的计算复杂性建立了下限。我们证明,自我注意力的时间复杂性在输入长度上必定是二次的,除非强烈的指数时间假设(SETH)是错误的。即使注意力计算仅执行大约和各种注意力机制,该论点也存在。作为对我们的下限的补充,我们表明确实可以使用有限的泰勒级数在线性时间中近似点产物自我发作,而成本依赖于多项式顺序。
translated by 谷歌翻译
利用预训练语言模型的抽象摘要系统在基准数据集上取得了卓越的结果。但是,此类模型已被证明更容易幻觉,这些事实对输入背景不忠。在本文中,我们提出了一种通过实体覆盖范围控制(ECC)来补救实体级外部幻觉的方法。我们首先计算实体覆盖范围的精度,并为每个培训示例提供相应的控制代码,该示例隐含地指导该模型在训练阶段识别忠实的内容。我们通过从Wikipedia提取的大但嘈杂的数据中进行中间调整进一步扩展了我们的方法,以解锁零击摘要。我们表明,根据我们对三个基准数据集XSUM,PubMed和Samsum的实验结果,根据我们在监督的微调和零射击设置中,可以在监督微调和零摄像设置中更加忠实和显着的抽象性汇总。
translated by 谷歌翻译
人工智能(AI)模型的黑框性质不允许用户理解和有时信任该模型创建的输出。在AI应用程序中,不仅结果,而且结果的决策路径至关重要,此类Black-Box AI模型还不够。可解释的人工智能(XAI)解决了此问题,并定义了用户可解释的一组AI模型。最近,有几种XAI模型是通过在医疗保健,军事,能源,金融和工业领域等各个应用领域的黑盒模型缺乏可解释性和解释性来解决有关的问题。尽管XAI的概念最近引起了广泛关注,但它与物联网域的集成尚未完全定义。在本文中,我们在物联网域范围内使用XAI模型对最近的研究进行了深入和系统的综述。我们根据其方法和应用领域对研究进行分类。此外,我们旨在专注于具有挑战性的问题和开放问题,并为未来的方向指导开发人员和研究人员进行未来的未来调查。
translated by 谷歌翻译
我们介绍了Hocalarim(MyProfescessors),是土耳其语的最大学生评论数据集。它包括超过5000多名教授的学生,教育的不同方面为1到5星的等级。我们调查数据集的属性并呈现其统计数据。我们研究学生机构类型对他们的评级的影响以及学生偏见的相关性,以提供积极或负面反馈。
translated by 谷歌翻译
我们对真正低资源语言的神经机翻译(NMT)进行了实证研究,并提出了一个训练课程,适用于缺乏并行培训数据和计算资源的情况,反映了世界上大多数世界语言和研究人员的现实致力于这些语言。以前,已经向低资源语言储存了使用后翻译(BT)和自动编码(AE)任务的无监督NMT。我们证明利用可比的数据和代码切换作为弱监管,与BT和AE目标相结合,即使仅使用适度的计算资源,低资源语言也会显着改进。在这项工作中提出的培训课程实现了Bleu分数,可通过+12.2 Bleu为古吉拉特和+3.7 Bleu为哈萨克斯培训的监督NMT培训,展示了弱势监督的巨大监督态度资源语言。在受到监督数据的培训时,我们的培训课程达到了索马里数据集(索马里29.3的BLEU的最先进的结果)。我们还观察到增加更多时间和GPU来培训可以进一步提高性能,强调报告在MT研究中的报告资源使用的重要性。
translated by 谷歌翻译