Orbit Weighting Scheme in the Context of Vector Space Information Retrieval

This study introduces the Orbit Weighting Scheme(OWS),a novel approach aimed at enhancing the precision and efficiency of Vector Space information retrieval(IR)models,which have traditionally relied on weighting schemes like tf-idf and BM25.These conventional methods often struggle with accurately capturing document relevance,leading to inefficiencies in both retrieval performance and index size management.OWS proposes a dynamic weighting mechanism that evaluates the significance of terms based on their orbital position within the vector space,emphasizing term relationships and distribution patterns overlooked by existing models.Our research focuses on evaluating OWS’s impact on model accuracy using Information Retrieval metrics like Recall,Precision,InterpolatedAverage Precision(IAP),andMeanAverage Precision(MAP).Additionally,we assessOWS’s effectiveness in reducing the inverted index size,crucial for model efficiency.We compare OWS-based retrieval models against others using different schemes,including tf-idf variations and BM25Delta.Results reveal OWS’s superiority,achieving a 54%Recall and 81%MAP,and a notable 38%reduction in the inverted index size.This highlights OWS’s potential in optimizing retrieval processes and underscores the need for further research in this underrepresented area to fully leverage OWS’s capabilities in information retrieval methodologies.

Region-Aware Fashion Contrastive Learning for Unified Attribute Recognition and Composed Retrieval

Clothing attribute recognition has become an essential technology,which enables users to automatically identify the characteristics of clothes and search for clothing images with similar attributes.However,existing methods cannot recognize newly added attributes and may fail to capture region-level visual features.To address the aforementioned issues,a region-aware fashion contrastive language-image pre-training(RaF-CLIP)model was proposed.This model aligned cropped and segmented images with category and multiple fine-grained attribute texts,achieving the matching of fashion region and corresponding texts through contrastive learning.Clothing retrieval found suitable clothing based on the user-specified clothing categories and attributes,and to further improve the accuracy of retrieval,an attribute-guided composed network(AGCN)as an additional component on RaF-CLIP was introduced,specifically designed for composed image retrieval.This task aimed to modify the reference image based on textual expressions to retrieve the expected target.By adopting a transformer-based bidirectional attention and gating mechanism,it realized the fusion and selection of image features and attribute text features.Experimental results show that the proposed model achieves a mean precision of 0.6633 for attribute recognition tasks and a recall@10(recall@k is defined as the percentage of correct samples appearing in the top k retrieval results)of 39.18 for composed image retrieval task,satisfying user needs for freely searching for clothing through images and texts.

Image Retrieval with Text Manipulation by Local Feature Modification

The demand for image retrieval with text manipulation exists in many fields, such as e-commerce and Internet search. Deep metric learning methods are used by most researchers to calculate the similarity between the query and the candidate image by fusing the global feature of the query image and the text feature. However, the text usually corresponds to the local feature of the query image rather than the global feature. Therefore, in this paper, we propose a framework of image retrieval with text manipulation by local feature modification(LFM-IR) which can focus on the related image regions and attributes and perform modification. A spatial attention module and a channel attention module are designed to realize the semantic mapping between image and text. We achieve excellent performance on three benchmark datasets, namely Color-Shape-Size(CSS), Massachusetts Institute of Technology(MIT) States and Fashion200K(+8.3%, +0.7% and +4.6% in R@1).

A Full Text Retrieval System in a Digital Library Environment

The volume of information being created, generated and stored is huge. Without adequate knowledge of Information Retrieval (IR) methods, the retrieval process for information would be cumbersome and frustrating. Studies have further revealed that IR methods are essential in information centres (for example, Digital Library environment) for storage and retrieval of information. Therefore, with more than one billion people accessing the Internet, and millions of queries being issued on a daily basis, modern Web search engines are facing a problem of daunting scale. The main problem associated with the existing search engines is how to avoid irrelevant information retrieval and to retrieve the relevant ones. In this study, the existing system of library retrieval was studied. Problems associated with them were analyzed in order to address this problem. The concept of existing information retrieval models was studied, and the knowledge gained was used to design a digital library information retrieval system. It was successfully implemented using a real life data. The need for a continuous evaluation of the IR methods for effective and efficient full text retrieval system was recommended.

Text retrieval algorithm that decreases confusion

To overcome the problem that the confusion between texts limits the precision in text re- trieval, a new text retrieval algorithm that decrease confusion （DCTR） is proposed. The algorithm constructs the searching template to represent the user＇ s searching intention through positive and negative training. By using the prior probabilities in the template, the supported probability and anti- supported probability of each text in the text library can be estimated for discrimination. The search- ing result can be ranked according to similarities between retrieved texts and the template. The com- plexity of DCTR is close to term frequency and mversed document frequency （TF-IDF）. Its distin- guishing ability to confusable texts could be advanced and the performance of the result would be im- proved with increasing of training times.

DI-VTR:Dual inter-modal interaction model for video-text retrieval

Video-text retrieval is a challenging task for multimodal information processing due to the semantic gap between different modalities.However,most existing methods do not fully mine the intra-modal interactions,as with the temporal correlation of video frames,which results in poor matching performance.Additionally,the imbalanced semantic information between videos and texts also leads to difficulty in the alignment of the two modalities.To this end,we propose a dual inter-modal interaction network for video-text retrieval,i.e.,DI-vTR.To learn the intra-modal interaction of video frames,we design a contextual-related video encoder to obtain more fine-grained content-oriented video representations.We also propose a dual inter-modal interaction module to accomplish accurate multilingual alignment between the video and text modalities by introducing multilingual text to improve the representation ability of text semantic features.Extensive experimental results on commonly-used video-text retrieval datasets,including MSR-VTT,MSVD and VATEX,show that the proposed method achieves significantly improved performance compared with state-of-the-art methods.

基于融合矩阵的文本相似度计算实现检索结果聚类

目的/意义弥补医学文本语义表示方面的不足,实现PubMed数据库检索结果聚类。方法/过程采用Jaccard系数和TF-IDF构建融合矩阵方法,建立短语间、文档间、短语与文档内容间的相似性关系融合矩阵,训练聚类算法,将PubMed数据库检索结果集合分组,随后生成类别标签,描述每一类簇文档的含义。结果/结论基于融合矩阵的聚类效果较好,提取出描述类别的高频词能很好地区分类别含义,对检索结果文本聚类任务有效。

数字化转型、分析师关注与企业创新绩效

企业与数字技术深度融合是实体经济发展的重要趋势。根据2008—2020年A股制造业微观企业数据,基于分析师关注视角研究企业数字化转型对创新绩效的作用及内在机理。结果显示:企业数字化进程明显促进了创新绩效的改善,且在一系列稳健性检验后该结论仍然成立;机制检验表明,数字化转型可以通过提高分析师关注度和降低分析师信息搜寻成本,进而改善企业创新绩效表现;异质性分析发现,微观层面,董事、监事等高管拥有海外背景的企业,数字化转型更有助于提高企业创新绩效水平;中观层面,供应链集中度较高和劳动密集型行业中的企业,数字化转型对企业创新绩效的激励效果会更弱;宏观层面,数字化转型对于处在环境不确定性较低和东部地区的企业,更有利于改善创新绩效。基于分析师关注视角研究有效拓展了数字化转型与企业创新的相关研究,为政府通过完善金融市场中介来推动创新驱动发展战略和现代化产业体系建设提供了经验证据。

文本语义哈希技术研究进展

文本语义哈希是在满足语义相似性约束下将文本转化为低维二值数据的神经编码技术,支持基于汉明距离的高效检索,以解决有限计算资源约束下海量文本的相似性计算问题。文本语义哈希技术存在诸多挑战,包括如何在低维二值编码中融入类别信息、如何丰富编码的语义信息以提升模型鲁棒性、如何解决离散输出的模型梯度估计等关键问题。文章首先综述文本语义哈希任务的重要研究发展,详细讨论了无监督文本语义哈希模型和融合类别信息的有监督文本语义哈希模型的技术细节,分析基于近邻文本、隐式主题等信息的语义增强技术以及模型优化等关键技术;然后,综述文本语义哈希任务相关数据集和评估指标,对比了各类文本语义哈希技术的特点和性能;最后,讨论了文本语义哈希技术的未来发展方向。

一种基于RoBERTa模型的文本搜索排序方法

针对日益增长的资料快速检索共享需求,利用鲁棒性优化的BERT方法(Robustly optimized BERT approach,RoBERTa)预训练模型对现有资料进行训练,基于Transformer自注意力机制的语言学习模型,生成文本嵌入向量,将文本向量作为全文本的上下文表征。通过将关键搜索词向量化,使用欧氏距离计算向量与其他向量之间的距离,并使用快速排序算法,以找到最相似的向量输出显示,解决基于内容和上下文语义搜索的应用需求。

面向业务的资源按需解析模型构建研究

针对在项目开发过程中新需求来临时,需要对自然语言处理工具和资源解析插件进行重新需求分析、重复开发等问题,提出了一套面向业务的资源按需解析方案。首先,提出了一种从需求到代码的资源按需解析方法,针对需求文本本身进行需求概念标引模型的构建。构建的需求概念标引模型的准确率、召回率、F1值等指标均高于其他分类模型。然后,针对需求文本与代码的关联,建立从需求文本到代码库类别的映射机制。对于模型的映射结果,使用前K准确率(percision@K)作为评价指标,最终准确率达到60%,具有一定的实用价值。综上所述,探索了一套具有需求解析能力、实现需求与代码关联的资源按需解析关键技术,并贯穿需求文本分类、需求代码库分类、代码库检索到插件生成的整个流程,形成了完整的“需求-代码-插件-解析”的业务闭环,通过实验验证了所提方法对于资源按需解析的有效性,为业务需求分析与软件复用提供了思路,与现有用于业务需求的解析和代码生成的大语言模型相比,所提方法聚焦于具体业务领域内的含有业务特点的插件代码复用全流程的实现。

利用BERT和覆盖率机制改进的HiNT文本检索模型

为有效提升文本语义检索的准确度,本文针对当前文本检索模型衡量查询和文档的相关性时不能很好地解决文本歧义和一词多义等问题,提出一种基于改进的分层神经匹配模型(hierarchical neural matching model,HiNT)。该模型先对文档的各个段提取关键主题词,然后用基于变换器的双向编码器(bidirectional encoder representations from transformers,BERT)模型将其编码为多个稠密的语义向量,再利用引入覆盖率机制的局部匹配层进行处理,使模型可以根据文档的局部段级别粒度和全局文档级别粒度进行相关性计算,提高检索的准确率。本文提出的模型在MS MARCO和webtext2019zh数据集上与多个检索模型进行对比,取得了最优结果,验证了本文提出模型的有效性。

CLIP4Video-Sampling: Global Semantics-Guided Multi-Granularity Frame Sampling for Video-Text Retrieval

Video-text retrieval (VTR) is an essential task in multimodal learning, aiming to bridge the semantic gap between visual and textual data. Effective video frame sampling plays a crucial role in improving retrieval performance, as it determines the quality of the visual content representation. Traditional sampling methods, such as uniform sampling and optical flow-based techniques, often fail to capture the full semantic range of videos, leading to redundancy and inefficiencies. In this work, we propose CLIP4Video-Sampling: Global Semantics-Guided Multi-Granularity Frame Sampling for Video-Text Retrieval, a global semantics-guided multi-granularity frame sampling strategy designed to optimize both computational efficiency and retrieval accuracy. By integrating multi-scale global and local temporal sampling and leveraging the CLIP (Contrastive Language-Image Pre-training) model’s powerful feature extraction capabilities, our method significantly outperforms existing approaches in both zero-shot and fine-tuned video-text retrieval tasks on popular datasets. CLIP4Video-Sampling reduces redundancy, ensures keyframe coverage, and serves as an adaptable pre-processing module for multimodal models.

基于特征增强和语义相关性匹配的图像文本检索方法

为实现图像文本检索中图像与文本的精确语义连接,提出一种基于特征增强和语义相关性匹配(FESCM)的图像文本检索方法。首先,通过特征增强表示模块,引入多头自注意力机制增强图像区域特征和文本单词特征,以减少冗余信息对图像区域和文本单词对齐的干扰;其次,通过语义相关性匹配模块,不仅利用局部匹配捕获局部显著对象之间的对应相关性,还把图像背景信息融入图像全局特征,利用全局匹配实现精确的全局语义相关性;最后,通过局部匹配分数和全局匹配分数获取图像和文本的最终匹配分数。实验结果表明,基于FESCM的图像文本检索方法在Flickr8k和Flickr30k基准数据集上的召回率总值比扩展的视觉语义嵌入方法分别提升了5.7和7.5个百分点,在MS-COCO数据集比双流层次相似度推理方法提升了3.7个百分点。因此该方法可以有效提高图像文本检索的准确度,实现图像与文本的语义连接。

基于ElasticSearch的医疗数据检索系统的设计与实现

随着医疗技术的发展,医疗业务场景越加复杂,由此产生的医疗数据也越来越多,其来源复杂,结构多变,信息冗余,数据不完整。这些特性使得系统在进行检索时,无法快速、有效、精确地查询数据。为了解决这个问题,设计并实现了基于ElasticSearch的医疗数据检索系统。该系统将医疗数据进行标准化,填补缺失值,选取合适的分词算法进行分词,将处理后的数据存入ElasticSearch中,同时使用SpringBoot构建系统应用,消耗多个医疗基础业务系统产生的数据,最终形成统一的医疗数据检索系统,给用户提供便捷、精确的查询服务。

基于知识增强的文本语义匹配模型研究

文本语义匹配模型在信息检索、文本挖掘等领域已经获得了广泛应用。为解决现有模型主要从文本自身角度判断文本之间的语义关系而忽略对外部知识有效利用的问题,本文提出一种新的基于知识增强的文本语义匹配模型,以知识图谱实体作为外部知识,有效建模文本的外部知识信息,并自适应地过滤外部知识中存在的噪声。针对自然语言推理和释义识别两个文本语义匹配任务,与基线方法相比,本文模型在大多数指标上取得了最优效果。研究结果表明,本文模型有助于揭示知识图谱在文本语义匹配任务中的作用,为将知识图谱应用到智能信息服务领域提供了参考。

嵌入共识知识的因果图文检索方法

跨模态图像-文本检索是一项在给定一种模态(如文本)的查询条件下检索另一种模态(如图像)的任务.该任务的关键问题在于如何准确地测量图文两种模态之间的相似性,在减少视觉和语言这两种异构模态之间的视觉语义差异中起着至关重要的作用.传统的检索范式依靠深度学习提取图像和文本的特征表示,并将其映射到一个公共表示空间中进行匹配.然而,这种方法更多地依赖数据表面的相关关系,无法挖掘数据背后真实的因果关系,在高层语义信息的表示和可解释性方面面临着挑战.为此,在深度学习的基础上引入因果推断和嵌入共识知识,提出嵌入共识知识的因果图文检索方法.具体而言,将因果干预引入视觉特征提取模块,通过因果关系替换相关关系学习常识因果视觉特征,并与原始视觉特征进行连接得到最终的视觉特征表示.为解决本方法文本特征表示不足的问题,采用更强大的文本特征提取模型BERT(Bidirectional encoder representations from transformers,双向编码器表示),并且嵌入两种模态数据之间共享的共识知识对图文特征进行共识级的表示学习.在MS-COCO数据集以及MS-COCO到Flickr30k上的跨数据集实验,证明了本文方法可以在双向图文检索任务上实现召回率和平均召回率的一致性改进.

基于关键实体和文本摘要多特征融合的话题匹配算法

随着网络的快速普及,互联网新闻的数量剧增,在这种情况下,如何有效地找到更加符合特定主题的相关报道成为一个迫切需要解决的问题。针对这一问题,提出了基于关键实体和文本摘要多特征融合的话题匹配算法。首先,使用W2NER模型进行命名实体识别,通过词频、TF-IDF、词的合群性、词词相似度和词句相似度特征,提取关键的实体。其次,使用Pegasus模型进行文本摘要,通过BiLSTM融合关键实体特征与文本摘要特征,得到新闻文本的深层次语义特征。再次,使用交叉注意力机制对待匹配新闻进行特征交互,增进彼此的联系。最后,融合新闻文本的深层次语义特征和文本交互特征,共同参与文本话题匹配的判断。在来自于搜狐的真实数据上进行了不同算法的对比实验,结果表明:所提算法准确率和精确率均与其他算法效果相近,召回率和F1值均有所提升。

基于多粒度语义融合的信息检索方法

信息检索(IR)是一种通过特定的技术和方法组织、处理信息,以满足用户的信息需求的过程。近年来,基于预训练模型的稠密检索方法取得了巨大的成功;然而,这些方法只利用了文本和词语的向量表征计算查询与文档相关度,忽略了它们短语层面间的语义信息。针对该问题,提出一种名为MSIR(Multi-Scale IR)的IR方法。所提方法通过融合查询与文档中多种不同粒度的语义信息提高IR性能。首先,构建查询和文档中词语、短语和文本这3个粒度的语义单元;其次,利用预训练模型对这3个语义单元分别进行编码获得它们的语义表征;最后,利用语义表征计算查询和文档相关度。在Corvid-19、TREC2019和Robust04这3个不同大小的经典数据集上进行了对比实验。与ColBERT(ranking model based on Contextualized late interaction over BERT(Bidirectional Encoder Representation from Transformers))相比,MSIR在Robust04数据集的P@10、P@20、NDCG@10和NDCG@20指标上均实现了约8%的提升,同时在Corvid-19和TREC2019数据集上也取得了一定的改进。实验结果表明,MSIR能够成功融合多种语义粒度,提升检索精度。

一种融合文本与知识图谱的问答系统模型

知识图谱是实现开放领域问答的关键技术之一,开放领域问答任务往往需要足够多的知识信息,而知识图谱的不完备性成为制约问答系统性能的重要因素。利用外部非结构化的文本与基于知识图谱的结构化知识相结合填补缺失信息时,检索外部文本的准确性和效率尤为关键,选取与问题相关度较高的文本可提升系统性能。相反,选取与问题相关性较弱的文本将引入知识噪声,降低问答任务的准确性。因此,设计了一种融合文本与知识图谱的问答系统模型,其中的文本检索器可充分挖掘问题和文本的语义信息,提高检索质量和查询子图的准确性;知识融合器将文本和知识库中的知识结合构建知识的融合表征。实验结果表明,相较对比模型,该模型在性能上存在一定优势。