Cross-Language Information Extraction and Auto Evaluation for OOV Term Translations

OOV term translation plays an important role in natural language processing. Although many researchers in the past have endeavored to solve the OOV term translation problems, but none existing methods offer definition or context information of OOV terms. Furthermore, non-existing methods focus on cross-language definition retrieval for OOV terms. Never the less, it has always been so difficult to evaluate the correctness of an OOV term translation without domain specific knowledge and correct references. Our English definition ranking method differentiate the types of OOV terms, and applies different methods for translation extraction. Our English definition ranking method also extracts multilingual context information and monolingual definitions of OOV terms. In addition, we propose a novel cross-language definition retrieval system for OOV terms. Never the less, we propose an auto re-evaluation method to evaluate the correctness of OOV translations and definitions. Our methods achieve high performances against existing methods.

Research on Cross-Language Retrieval Using Bilingual Word Vectors in Different Languages

Bilingual word vectors have been exploited a lot in cross-language information retrieval research. However, most of the research is currently focused on similar language pairs. There are very few studies exploring the impact of using bilingual word vectors for cross-language information retrieval in long-distance language pairs. In this paper, it systematically analyzes the retrieval performance of various European languages (English, German, Italian, French, Finnish, Dutch) as well as Asian languages (Chinese, Japanese) in the adhoc task of CLEF 2002–2003 campaign. Genetic proximity was used to visually represent the relationships between languages and compare their crosslingual retrieval performance in various settings. The results show that the differences in language vocabulary would dramatically affect the retrieval performance. At the same time, the term by term translation retrieval method performs slightly better than the simple vector addition retrieval methods. It proves that the translation-based retrieval model can still maintain its advantage under the new semantic scheme.

Query Expansion for Chinese Information Retrieval by Using a Decaying Co-occurrence Model

Query expansion with thesaurus is one of the useful techniques in modern information retrieval (IR). In this paper, a method of query expansion for Chinese IR by using a decaying co-occurrence model is proposed and realized. The model is an extension of the traditional co-occurrence model by adding a decaying factor that decreases the mutual information when the distance between the terms increases. Experimental results on TREC-9 collections show this query expansion method results in significant improvements over the IR without query expansion.

A new approach to query expansion in information retrieval

To eliminate the mismatch between words of relevant documents and user's query and more seriousnegative effects it has on the performance of information retrieval,a method of query expansion on the ba-sis of new terms co-occurrence representation was put forward by analyzing the process of producingquery.The expansion terms were selected according to their correlation to the whole query.At the sametime,the position information between terms were considered.The experimental result on test retrievalconference(TREC)data collection shows that the method proposed in the paper has made an improve-ment of 5%～19% all the time than the language modeling method without expansion.Compared to thepopular approach of query expansion,pseudo feedback,the precision of the proposed method is competi-tive.

New Retrieval Method Based on Relative Entropy for LanguageModeling with Different Smoothing Methods

A language model for information retrieval is built by using a query language model to generate queries and a document language model to generate documents. The documents are ranked according to the relative entropies of estimated document language models with respect to the estimated query language model. Two popular and relatively efficient smoothing methods, the Jelinek- Mercer method and the absolute discounting method, are used to smooth the document language model in estimation of the document language, A combined model composed of the feedback document language model and the collection language model is used to estimate the query model. A performacne comparison between the new retrieval method and the existing method with feedback is made, and the retrieval performances of the proposed method with the two different smoothing techniques are evaluated on three Text Retrieval Conference （TREC） data sets. Experimental results show that the method is effective and performs better than the basic language modeling approach; moreover, the method using the Jelinek-Mercer technique performs better than that using the absolute discounting technique, and the perfomance is sensitive to the smoothing peramters.

Natural Language Processing with Optimal Deep Learning-Enabled Intelligent Image Captioning System

The recent developments in Multimedia Internet of Things(MIoT)devices,empowered with Natural Language Processing(NLP)model,seem to be a promising future of smart devices.It plays an important role in industrial models such as speech understanding,emotion detection,home automation,and so on.If an image needs to be captioned,then the objects in that image,its actions and connections,and any silent feature that remains under-projected or missing from the images should be identified.The aim of the image captioning process is to generate a caption for image.In next step,the image should be provided with one of the most significant and detailed descriptions that is syntactically as well as semantically correct.In this scenario,computer vision model is used to identify the objects and NLP approaches are followed to describe the image.The current study develops aNatural Language Processing with Optimal Deep Learning Enabled Intelligent Image Captioning System(NLPODL-IICS).The aim of the presented NLPODL-IICS model is to produce a proper description for input image.To attain this,the proposed NLPODL-IICS follows two stages such as encoding and decoding processes.Initially,at the encoding side,the proposed NLPODL-IICS model makes use of Hunger Games Search(HGS)with Neural Search Architecture Network(NASNet)model.This model represents the input data appropriately by inserting it into a predefined length vector.Besides,during decoding phase,Chimp Optimization Algorithm(COA)with deeper Long Short Term Memory(LSTM)approach is followed to concatenate the description sentences 4436 CMC,2023,vol.74,no.2 produced by the method.The application of HGS and COA algorithms helps in accomplishing proper parameter tuning for NASNet and LSTM models respectively.The proposed NLPODL-IICS model was experimentally validated with the help of two benchmark datasets.Awidespread comparative analysis confirmed the superior performance of NLPODL-IICS model over other models.

基于类型矩阵转移的汉越事件因果关系识别

针对汉越跨语言新闻事件因果关系识别中,汉越跨语言的文本语义空间难以统一、新闻之间的因果关联特征捕获困难的问题,提出了基于类型矩阵转移的汉越跨语言新闻事件因果关系识别方法。通过跨语言预训练统一汉越跨语言的文本语义空间,使用树形长短期记忆循环神经网络提取汉越文本中的句法结构化特征,融入汉越句法特征并结合基于事件类型转移的注意力机制,对汉越事件句对的因果关系进行识别。实验结果表明,该方法在汉越跨语言新闻事件因果关系的识别上较基线模型准确率有所提升。

特征融合的装修案例跨模态检索方法

目前家装客服系统中主要依靠人工方式进行装修案例检索,导致该系统不能满足用户对咨询服务快捷、及时的需求而且人力成本高,故提出一种基于特征融合的装修案例跨模态检索算法。针对多模态数据的语义信息挖掘不充分,模型检索精度低等问题,对现有的风格聚合模块进行改进,在原始模块中引入通道注意力机制,以此来为每组装修案例中不同图片的特征向量添加合适的权重,从而增强包含更多有用信息的重要特征并削弱其他不重要的特征。同时,为充分利用多模态信息,设计一种适用于检索场景下的多模态特征融合模块,该模块能够自适应地控制2种不同模态的特征向量进行一系列的融合操作,以实现跨模态数据间的知识流动与共享,从而生成语义更丰富、表达能力更强的特征向量,进一步提升模型的检索性能。在自建的装修案例多模态数据集上将该方法与其他方法进行比较,试验结果表明本文方法在装修案例检索上具有更优越的性能。

基于大模型的电子信息领域知识图谱自动构建与检索技术

当前电子信息领域积累的越来越多宝贵经验知识对知识使用技术提出了新的挑战。知识图谱(Knowledge Graph, KG)技术和大规模预训练语言模型(Large Language Model, LLM)技术在知识使用方面都各自存在缺陷,但两种技术的优缺点能够形成互补。因此,基于LLM技术,提出了应用于电子信息领域的知识图谱自动构建与检索增强问答技术。首先基于LLM的语义理解能力自动构建电子信息领域知识图谱,然后构建基于知识图谱和检索增强大模型的知识问答系统。在CoNLL2003数据集和构建的电子信息领域数据集上的实验证明了所方法具有较好质量,知识问答系统具有较好的实用效果。所提方法能够更好地满足从业人员从海量文档中提取相关知识,提高知识利用效率的迫切需求,为推动大模型结合知识图谱技术在电子信息垂直领域的落地应用提供参考。

基于图卷积的无监督跨模态哈希检索算法

为解决当前无监督跨模态哈希检索在全局相似性矩阵构建和异构数据语义信息融合中存在的困难,提出一种基于图卷积的无监督跨模态哈希检索算法(GCUH)。采用分层次聚合的方式,将各个模态的相似性结构编码到全局相似性矩阵中,获得跨模态的成对相似性信息来指导学习。使用图卷积模块融合跨模态信息,消除邻居结构中的噪声干扰,形成完备的跨模态表征,提出两种相似性保持的损失函数约束哈希码的一致性。与基线模型相比,GCUH在NUS-WIDE数据集上使用64位哈希码执行文本检索图片任务的检索精度提升了6.3%。

大语言模型增强的知识图谱问答研究进展综述

知识图谱问答(knowledge graph question answering,KGQA)是一种通过处理用户提出的自然语言问题,从知识图谱中获取相关答案的技术。早期的知识图谱问答技术受到知识图谱规模、计算能力以及自然语言处理能力的限制,准确率较低。近年来,随着人工智能技术的进步,特别是大语言模型(large language model,LLM)的发展,知识图谱问答技术的性能得到显著提升。大语言模型如GPT-3等已经被广泛应用于增强知识图谱问答的性能。为了更好地研究学习增强知识图谱问答的技术,对现有的各种大语言模型增强的知识图谱问答方法进行了归纳分析。总结了大语言模型和知识图谱问答的相关知识,即大语言模型的技术原理、训练方法,以及知识图谱、问答和知识图谱问答的基本概念。从语义解析和信息检索两个维度,综述了大语言模型增强知识图谱问答的现有方法,分析了方法所解决的问题及其局限性。收集整理了大语言模型增强知识图谱问答的相关资源和评测方法,并对现有方法的性能表现进行了总结。最后针对现有方法的局限性,分析并提出了未来的重点研究方向。

面向汉越跨语言事件检索的事件预训练方法

汉越跨语言事件检索是用汉语查询检索越南语事件新闻的任务。由于越南语属于典型的低资源语言,汉越跨语言事件检索缺乏大规模的标注数据,并且现有的跨语言预训练模型无法很好地表征文本中丰富的汉越对齐事件知识,不适用于该任务。因此,为了将汉越双语对齐的事件知识融入到多语言预训练语言模型中,该文提出了两个预训练方法,即事件要素掩码预训练以及跨语言事件对比预训练。在该文构造的汉越跨语言事件检索数据集和公开跨语言问答数据集上进行了实验,比基线提升1%~3%MAP值,2%~4%NDCG值,证明了该文方法的有效性。

基于布局化-语义联合表征遥感图文检索方法

遥感图文检索可以从类别繁多、内容复杂的遥感数据中检索到有价值的信息,对环境评估、城市规划以及灾害预测具有重要意义。但是,遥感图文跨模态检索存在一个关键问题,即遥感图像的空间布局信息被忽略。其主要体现在2个方面:①遥感目标的远距离建模困难;②遥感相邻次要目标被淹没。基于以上问题,提出了一种基于布局化-语义联合表征的跨模态遥感图像文本检索(SL-SJR),主要包括主导语义监督的布局化视觉特征提取(DSSL)模块、布局化视觉-全局语义交叉指导(LV-GSCG)模块和多视角匹配(MVM)模块。DSSL模块实现主导语义类别特征监督下图像的布局化建模。LV-GSCG模块计算布局化视觉特征与文本中提取的全局语义特征的相似度来实现不同模态特征的交互。MVM模块建立跨模态特征指导的多视角度量匹配机制以消除跨模态数据之间的语义鸿沟。在4个基线遥感图像文本数据集上的实验验证,结果表明所提方法在大多数跨模态遥感图像文本检索任务中可以达到最先进的性能。

基于提示学习的轻量化代码生成方法

代码自动生成是提高软件开发效率的有效途径之一,已有的研究一般将代码生成作为一项序列到序列的任务,并且大规模预训练语言模型的微调过程往往伴随着高昂的算力开销。文中提出了一种基于提示学习的轻量化代码生成方法(Prompt Learning based Parameter-Efficient Code Generation,PPECG),该方法通过查询代码语料库中与当前需求最相似的结果作为提示,指导预训练语言模型进行代码生成,并且在该过程中固定模型的绝大多数参数以实现减少算力开销的目的。为了验证PPECG的有效性,文中选取了两个代码生成数据集,分别是CONCODE和Solidity4CG,通过计算生成结果的BLEU,CodeBLEU以及Exact Match值来验证PPECG的有效性,实验结果表明,PPECG有效地减少了微调时的显存开销,且在上述指标上基本接近甚至优于目前的SOTA方法,能够较好地完成代码生成的任务。

基于知识图谱的零样本文档检索伪查询生成

为提高文档检索模型性能,减轻手工标记训练数据的工作量,提出一种基于知识图谱的零样本文档检索伪查询生成方法KGQG。该方法利用知识图谱增强伪查询,将外部信息与伪查询相结合,以生成更丰富、更具信息量的伪查询。实验结果表明,在BEIR基准测试的12个公开数据集中,KGQG方法比经典的稀疏检索模型、稠密检索模型以及最新的基于外部知识扩展的零样本稠密检索模型在归一化折现累计效益(NDCG)指标方面分别提升了4.6、11.88、7.96个百分点。KGQG方法不仅能提高检索性能,而且减少了手动标记训练数据需求,为文档检索模型的未来研究与应用提供了有益参考。

基于层次聚类的图文检索模型研究

图文检索在工业中的用途和作用是多方面的,可以帮助提高研发和生产效率,促进科技创新,提高产品的质量和竞争力;目前,图文检索模型的重点是提高检索的精度;随着技术和数据的快速发展,深度学习和大模型技术的不断应用,图文检索的速度问题逐渐凸显,为解决当前图文检索速度受限、计算量大的问题,提出了一种基于层次聚类的图文检索模型;该方法选择了检索效果明显的跨模态哈希方法,并运用深度聚类算法对待检索的数据进行分类,从而缩小检索范围,提高了检索速度;实验结果表明,基于层次聚类的图文检索模型在保持检索精度的同时,显著提高了检索速度,使得工程人员能够更快地获取到满意的检索结果。

面向业务需求的知识增强大模型生成框架技术研究

近年来,大模型技术方兴未艾,在通用领域获得长足发展。然而,在军事、政务等关键领域训练数据不足导致专业领域的大模型应用能力难以满足用户的需求,特别是针对业务需求的多类型数据检索任务,通用大模型存在瓶颈。本文提出一种知识增强的大模型跨数据检索框架,设计一种知识融合生长的大模型检索能力演进机制,利用大模型的自监督信号驱动领域知识持续生成,同时利用积累的知识持续增强大模型检索能力,在典型业务场景下开展原型系统构建与试验验证,在典型场景下检验框架对用户业务信息的查询与结果生成能力,实验结果表明,高质量的知识有助于提高大模型生成结果的精准性与有效性。

基于Go语言的安标产品信息检索系统设计

本文介绍了一款基于Go语言的安标产品信息管理查询系统软件实现方法,该系统软件通过网络请求获取安标产品的综合信息,并打印显示出查询结果,同时将结果自动保存在Excel文件中。通过检索关键字,用户能够快速获取相关产品的详细信息,实现了安标产品信息的快速检索与查询。论文详细阐述了基于Go语言的软件设计思路、实现过程和功能特点、实际应用场景和未来的改进方向。