Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on a wide range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that cross-encoders largely outperform bi-encoders of similar size in several tasks. In the BEIR benchmark, our largest cross-encoder surpasses a state-of-the-art bi-encoder by more than 4 average points. Finally, we show that using bi-encoders as first-stage retrievers provides no gains in comparison to a simpler retriever such as BM25 on out-of-domain tasks. The code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git
translated by 谷歌翻译
Robust 2004是一种信息检索基准,其每个查询的大量判断使其成为可靠的评估数据集。在本文中,我们介绍了Mrobust04,这是一种多语言版本的robust04,使用Google Translate翻译为8种语言。我们还提供了该数据集上三个不同多语言检索器的结果。该数据集可在https://huggingface.co/datasets/unicamp-dl/mrobust上获得
translated by 谷歌翻译
最近的工作表明,小型蒸馏语言模型是强大的竞争对手,这些模型是在广泛的信息检索任务中更大且较慢的数量级。由于潜伏期的限制,这使蒸馏而密集的模型是在现实世界检索应用程序中部署的首选选择。在这项工作中,我们通过证明参数和早期查询文档互动的数量在检索模型的概括能力中起着重要作用来质疑这种做法。我们的实验表明,增加模型大小会导致内域测试集的边际增长,但是在微调过程中从未见过的新领域的增长幅度更大。此外,我们表明,在几个任务中,Rerankers在很大程度上都超过了相似大小的密集。我们最大的重读者在基准-IR(BEIR)的18个数据集中的12个数据集中达到了最新技术,并超过了先前的最新水平。最后,我们确认内域的有效性不是零弹性有效性的良好指标。代码可从https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git获得。
translated by 谷歌翻译
MARCO排名数据集已广泛用于培训IR任务的深度学习模型,在不同的零射击方案上实现了相当大的效果。但是,这种类型的资源是英语以外的语言的稀缺。在这项工作中,我们呈现MMARCO,MS Marco段落的多语言版本,该数据集包括使用机器翻译创建的13种语言。我们通过微调单语和多语言重新排名模型以及此数据集的密集多语言模型进行了评估。实验结果表明,在我们翻译的数据集上微调微调的多语言模型可以单独对原始英文版的模型进行微调的卓越效果。我们蒸馏的多语言RE-RANKER与非蒸馏模型具有竞争力,而参数较少的5.4倍。最后,我们展现了翻译质量和检索效果之间的正相关性,提供了证据,即翻译方法的改进可能导致多语言信息检索的改进。翻译的数据集和微调模型可在https://github.com/unicamp-dl/mmarco.git上获得。
translated by 谷歌翻译
In this work a novel recommender system (RS) for Tourism is presented. The RS is context aware as is now the rule in the state-of-the-art for recommender systems and works on top of a tourism ontology which is used to group the different items being offered. The presented RS mixes different types of recommenders creating an ensemble which changes on the basis of the RS's maturity. Starting from simple content-based recommendations and iteratively adding popularity, demographic and collaborative filtering methods as rating density and user cardinality increases. The result is a RS that mutates during its lifetime and uses a tourism ontology and natural language processing (NLP) to correctly bin the items to specific item categories and meta categories in the ontology. This item classification facilitates the association between user preferences and items, as well as allowing to better classify and group the items being offered, which in turn is particularly useful for context-aware filtering.
translated by 谷歌翻译
Wearable sensor-based human activity recognition (HAR) has emerged as a principal research area and is utilized in a variety of applications. Recently, deep learning-based methods have achieved significant improvement in the HAR field with the development of human-computer interaction applications. However, they are limited to operating in a local neighborhood in the process of a standard convolution neural network, and correlations between different sensors on body positions are ignored. In addition, they still face significant challenging problems with performance degradation due to large gaps in the distribution of training and test data, and behavioral differences between subjects. In this work, we propose a novel Transformer-based Adversarial learning framework for human activity recognition using wearable sensors via Self-KnowledgE Distillation (TASKED), that accounts for individual sensor orientations and spatial and temporal features. The proposed method is capable of learning cross-domain embedding feature representations from multiple subjects datasets using adversarial learning and the maximum mean discrepancy (MMD) regularization to align the data distribution over multiple domains. In the proposed method, we adopt the teacher-free self-knowledge distillation to improve the stability of the training procedure and the performance of human activity recognition. Experimental results show that TASKED not only outperforms state-of-the-art methods on the four real-world public HAR datasets (alone or combined) but also improves the subject generalization effectively.
translated by 谷歌翻译
使用机器学习算法从未标记的文本中提取知识可能很复杂。文档分类和信息检索是两个应用程序,可以从无监督的学习(例如文本聚类和主题建模)中受益,包括探索性数据分析。但是,无监督的学习范式提出了可重复性问题。初始化可能会导致可变性,具体取决于机器学习算法。此外,关于群集几何形状,扭曲可能会产生误导。在原因中,异常值和异常的存在可能是决定因素。尽管初始化和异常问题与文本群集和主题建模相关,但作者并未找到对它们的深入分析。这项调查提供了这些亚地区的系统文献综述(2011-2022),并提出了共同的术语,因为类似的程序具有不同的术语。作者描述了研究机会,趋势和开放问题。附录总结了与审查的作品直接或间接相关的文本矢量化,分解和聚类算法的理论背景。
translated by 谷歌翻译
现代的3D计算机视觉利用学习来增强几何推理,将图像数据映射到经典结构,例如成本量或外观限制,以改善匹配。这些体系结构根据特定问题进行了专门化,因此需要进行大量任务的调整,通常会导致域的泛化性能差。最近,通才变压器架构通过编码几何学先验作为输入而不是执行约束,在诸如光流和深度估计等任务中取得了令人印象深刻的结果。在本文中,我们扩展了这一想法,并建议学习一个隐式,多视图一致的场景表示,并在增加视图多样性之前引入了一系列3D数据增强技术作为几何感应。我们还表明,引入视图合成作为辅助任务进一步改善了深度估计。我们的深度磁场网络(定义)实现了最新的目的,可以实现立体声和视频深度估计,而无需明确的几何约束,并通过广泛的边距改善了零局部域的概括。
translated by 谷歌翻译
3D多对象跟踪旨在唯一,始终如一地识别所有移动实体。尽管在此设置中提供了丰富的时空信息,但当前的3D跟踪方法主要依赖于抽象的信息和有限的历史记录,例如单帧对象边界框。在这项工作中,我们开发了对交通场景的整体表示,该场景利用了现场演员的空间和时间信息。具体而言,我们通过将跟踪的对象表示为时空点和边界框的序列来重新将跟踪作为时空问题,并在悠久的时间历史上进行重新制定。在每个时间戳上,我们通过对对象历史记录的完整顺序进行的细化来改善跟踪对象的位置和运动估计。通过共同考虑时间和空间,我们的代表自然地编码了基本的物理先验,例如对象持久性和整个时间的一致性。我们的时空跟踪框架在Waymo和Nuscenes基准测试中实现了最先进的性能。
translated by 谷歌翻译
在自然语言处理中,已证明使用预训练的语言模型可以在许多下游任务(例如情感分析,作者识别等)中获得最先进的结果。在这项工作中,我们解决了这些方法从文本中使用的人格分类。着眼于Myers-Briggs(MBTI)人格模型,我们描述了一系列实验,其中众所周知的双向编码器表示来自变形金刚(BERT)模型的模型进行微调以执行MBTI分类。我们的主要发现表明,当前方法在多种评估方案中基于词袋和静态单词嵌入方式大大优于众所周知的文本分类模型,并且通常在该领域的先前工作都优于先前的工作。
translated by 谷歌翻译