The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situati...The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.展开更多
Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications li...Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.展开更多
Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algeb...Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algebraic subsets of G forms a family of closed sets for another T_(1)topology Z_(G) on G called the Zarski topology.A subgroup H of G is said to be Markov(resp.Zarski)embedded if the equality M_(G|H)=M_(H)(resp.Z_(G|H)=Z_(H))holds.I's proved that an abirary subgroup of a free group is both Zariski and Markov embedded in it.展开更多
Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been i...Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been implemented to represent the chemical structure in machine learning models,among which Mol2Vec embeddings have attracted considerable attention in the cheminformatics community since their introduction in 2018.However,for small datasets,the use of chemical structure representations typically increases the dimensionality of the input dataset,resulting in a decrease in model performance.Furthermore,the limited diversity of polymer chemical structures hinders the training of reliable embeddings,necessitating complex task-specific architecture implementations.To address these challenges,we examined the efficacy of Mol2Vec pre-trained embeddings in deriving vectorized representations of polymers.This study assesses the impact of incorporating Mol2Vec compound vectors into the input features on the efficacy of a model reliant on the physical properties of 214 polymers.The results will hopefully highlight the potential for improving prediction accuracy in polymer studies by incorporating pre-trained embeddings or promote their utilization when dealing with modestly sized polymer databases.展开更多
In this paper,by constructing the current graph of the complete graph K_(12s+9)and a mapping function,we prove that K_(12s+9)(s is an odd number)has at least 6^(2s)×3^(s+3/2) nonisomorphic orientable quadrangular...In this paper,by constructing the current graph of the complete graph K_(12s+9)and a mapping function,we prove that K_(12s+9)(s is an odd number)has at least 6^(2s)×3^(s+3/2) nonisomorphic orientable quadrangular embeddings,and the orientable genus is(12s+9)(12s+4)/8+1.Every one of the nonisomorphic orientable quadrangular embeddings has at least twenty-four 4-edge-colors,and each color appears around each face of orientable quadrangular embeddings.展开更多
One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse ...One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.展开更多
随着民航经济的发展和人民生活水平的提高,旅客出行的服务要求越来越高,而当前传统的民航客服知识库检索普遍存在检索准确率以及效率低的问题,已经不能满足旅客的服务需求。文章通过结合Best Match 25算法、文本Embeddings和交叉编码器...随着民航经济的发展和人民生活水平的提高,旅客出行的服务要求越来越高,而当前传统的民航客服知识库检索普遍存在检索准确率以及效率低的问题,已经不能满足旅客的服务需求。文章通过结合Best Match 25算法、文本Embeddings和交叉编码器对知识库进行检索,高效检索出符合座席意图的答案,进而提升民航客服知识库查找效率,缩短座席通话查询时长,提升旅客服务体验,助力实现民航客服数字化、智能化转型。展开更多
The substantial competition among the news industries puts editors under the pressure of posting news articleswhich are likely to gain more user attention. Anticipating the popularity of news articles can help the edi...The substantial competition among the news industries puts editors under the pressure of posting news articleswhich are likely to gain more user attention. Anticipating the popularity of news articles can help the editorial teamsin making decisions about posting a news article. Article similarity extracted from the articles posted within a smallperiod of time is found to be a useful feature in existing popularity prediction approaches. This work proposesa new approach to estimate the popularity of news articles by adding semantics in the article similarity basedapproach of popularity estimation. A semantically enriched model is proposed which estimates news popularity bymeasuring cosine similarity between document embeddings of the news articles. Word2vec model has been used togenerate distributed representations of the news content. In this work, we define popularity as the number of timesa news article is posted on different websites. We collect data from different websites that post news concerning thedomain of cybersecurity and estimate the popularity of cybersecurity news. The proposed approach is comparedwith different models and it is shown that it outperforms the other models.展开更多
The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification systems.Due to its importance,numerous studies have been conducted in...The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification systems.Due to its importance,numerous studies have been conducted in various languages.Researchers have established several learning methods for writer identification including supervised and unsupervised learning.However,supervised methods require a large amount of annotation data,which is impossible in most scenarios.On the other hand,unsupervised writer identification methods may be limited and dependent on feature extraction that cannot provide the proper objectives to the architecture and be misinterpreted.This paper introduces an unsupervised writer identification system that analyzes the data and recognizes the writer based on the inter-feature relations of the data to resolve the uncertainty of the features.A pairwise architecturebased Autoembedder was applied to generate clusterable embeddings for handwritten text images.Furthermore,the trained baseline architecture generates the embedding of the data image,and the K-means algorithm is used to distinguish the embedding of individual writers.The proposed model utilized the IAM dataset for the experiment as it is inconsistent with contributions from the authors but is easily accessible for writer identification tasks.In addition,traditional evaluation metrics are used in the proposed model.Finally,the proposed model is compared with a few unsupervised models,and it outperformed the state-of-the-art deep convolutional architectures in recognizing writers based on unlabeled data.展开更多
Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meani...Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meanings of a polysemous entity share one embedding vector.This study aims to propose a polysemous embedding approach,named KG embedding under relational contexts(ContE for short),for missing link prediction.Design/methodology/approach:ContE models and infers different relationship patterns by considering the context of the relationship,which is implicit in the local neighborhood of the relationship.The forward and backward impacts of the relationship in ContE are mapped to two different embedding vectors,which represent the contextual information of the relationship.Then,according to the position of the entity,the entity’s polysemous representation is obtained by adding its static embedding vector to the corresponding context vector of the relationship.Findings:ContE is a fully expressive,that is,given any ground truth over the triples,there are embedding assignments to entities and relations that can precisely separate the true triples from false ones.ContE is capable of modeling four connectivity patterns such as symmetry,antisymmetry,inversion and composition.Research limitations:ContE needs to do a grid search to find best parameters to get best performance in practice,which is a time-consuming task.Sometimes,it requires longer entity vectors to get better performance than some other models.Practical implications:ContE is a bilinear model,which is a quite simple model that could be applied to large-scale KGs.By considering contexts of relations,ContE can distinguish the exact meaning of an entity in different triples so that when performing compositional reasoning,it is capable to infer the connectivity patterns of relations and achieves good performance on link prediction tasks.Originality/value:ContE considers the contexts of entities in terms of their positions in triples and the relationships they link to.It decomposes a relation vector into two vectors,namely,forward impact vector and backward impact vector in order to capture the relational contexts.ContE has the same low computational complexity as TransE.Therefore,it provides a new approach for contextualized knowledge graph embedding.展开更多
In this paper, the authors discuss the upper bound for the genus of strong embeddings for 3-connected planar graphs on higher surfaces. It is shown that the problem of determining the upper bound for the strong embedd...In this paper, the authors discuss the upper bound for the genus of strong embeddings for 3-connected planar graphs on higher surfaces. It is shown that the problem of determining the upper bound for the strong embedding of 3-connected planar near-triangulations on higher non-orientable surfaces is NP-hard. As a corollary, a theorem of Richter, Seymour and Siran about the strong embedding of 3-connected planar graphs is generalized to orientable surface.展开更多
In this paper, it is shown that for every maximal planar graph G=(V,E) , a strong embedding on some non orientable surface with genus at most |V(G)|-22 is admitted such that the surface dual of G is also a...In this paper, it is shown that for every maximal planar graph G=(V,E) , a strong embedding on some non orientable surface with genus at most |V(G)|-22 is admitted such that the surface dual of G is also a planar graph. As a corollary, an interpolation theorem for strong embeddings of G on non orientable surfaces is obtained.展开更多
The concept of coarse embedding appears in various contexts of geometry,group theory,analysis,and theoretical computer science.The purpose of this paper is to motivate the concept,give an account of its origin,and sur...The concept of coarse embedding appears in various contexts of geometry,group theory,analysis,and theoretical computer science.The purpose of this paper is to motivate the concept,give an account of its origin,and survey development of the topic.展开更多
In this paper we show that the face-width of any embedding of a Halin graph（a type of planar graph） in the torus is one, and give a formula for determining the number of all nonequivalent embeddings of a Halin graph...In this paper we show that the face-width of any embedding of a Halin graph（a type of planar graph） in the torus is one, and give a formula for determining the number of all nonequivalent embeddings of a Halin graph in the torus.展开更多
We study embeddings between generalised Triebel–Lizorkin–Morrey spacesε_(ϕ,p,q)^(s)(R^(d))and within the scales of further generalised Morrey smoothness spaces like N_(ϕ,p,q)^(s)(R^(d)),B_(p,q)^(s,ϕ)(R^(d))and F_(p...We study embeddings between generalised Triebel–Lizorkin–Morrey spacesε_(ϕ,p,q)^(s)(R^(d))and within the scales of further generalised Morrey smoothness spaces like N_(ϕ,p,q)^(s)(R^(d)),B_(p,q)^(s,ϕ)(R^(d))and F_(p,q)^(s,ϕ)(R^(d)).The latter have been investigated in a recent paper by the first two authors(2023),while the embeddings of the scale N_(ϕ,p,q)^(s)(R^(d))were mainly obtained in a paper of the first and last two authors(2022).Now we concentrate on the characterisation of the spacesε_(ϕ,p,q)^(s)(R^(d)).Our approach requires a wavelet characterisation of those spaces which we establish for the system of Daubechies’wavelets.Then we prove necessary and sufficient conditions for the embeddingε_(ϕ1,p1,q1)^(s1)(R^(d))→ε_(2ϕ2,p2,q2)^(s)(R^(d)).We can also provide some almost final answer to the question whenε_(ϕ,p,q)^(s)(R^(d))is embedded into C(R^(d)),complementing our recent findings in case of N_(ϕ,p,q)^(s)(R^(d)).展开更多
Purpose:The paper aims to enhance Arabic machine translation(MT)by proposing novel approaches:(1)a dimensionality reduction technique for word embeddings tailored for Arabic text,optimizing efficiency while retaining ...Purpose:The paper aims to enhance Arabic machine translation(MT)by proposing novel approaches:(1)a dimensionality reduction technique for word embeddings tailored for Arabic text,optimizing efficiency while retaining semantic information;(2)a comprehensive comparison of meta-embedding techniques to improve translation quality;and(3)a method leveraging self-attention and Gated CNNs to capture token dependencies,including temporal and hierarchical features within sentences,and interactions between different embedding types.These approaches collectively aim to enhance translation quality by combining different embedding schemes and leveraging advanced modeling techniques.Design/methodology/approach:Recent works on MT in general and Arabic MT in particular often pick one type of word embedding model.In this paper,we present a novel approach to enhance Arabic MT by addressing three key aspects.Firstly,we propose a new dimensionality reduction technique for word embeddings,specifically tailored for Arabic text.This technique optimizes the efficiency of embeddings while retaining their semantic information.Secondly,we conduct an extensive comparison of different meta-embedding techniques,exploring the combination of static and contextual embeddings.Through this analysis,we identify the most effective approach to improve translation quality.Lastly,we introduce a novel method that leverages self-attention and Gated convolutional neural networks(CNNs)to capture token dependencies,including temporal and hierarchical features within sentences,as well as interactions between different types of embeddings.Our experimental results demonstrate the effectiveness of our proposed approach in significantly enhancing Arabic MT performance.It outperforms baseline models with a BLEU score increase of 2 points and achieves superior results compared to state-of-the-art approaches,with an average improvement of 4.6 points across all evaluation metrics.Findings:The proposed approaches significantly enhance Arabic MT performance.The dimensionality reduction technique improves the efficiency of word embeddings while preserving semantic information.Comprehensive comparison identifies effective meta-embedding techniques,with the contextualized dynamic meta-embeddings(CDME)model showcasing competitive results.Integration of Gated CNNs with the transformer model surpasses baseline performance,leveraging both architectures’strengths.Overall,these findings demonstrate substantial improvements in translation quality,with a BLEU score increase of 2 points and an average improvement of 4.6 points across all evaluation metrics,outperforming state-of-the-art approaches.Originality/value:The paper’s originality lies in its departure from simply fine-tuning the transformer model for a specific task.Instead,it introduces modifications to the internal architecture of the transformer,integrating Gated CNNs to enhance translation performance.This departure from traditional fine-tuning approaches demonstrates a novel perspective on model enhancement,offering unique insights into improving translation quality without solely relying on pre-existing architectures.The originality in dimensionality reduction lies in the tailored approach for Arabic text.While dimensionality reduction techniques are not new,the paper introduces a specific method optimized for Arabic word embeddings.By employing independent component analysis(ICA)and a post-processing method,the paper effectively reduces the dimensionality of word embeddings while preserving semantic information which has not been investigated before especially for MT task.展开更多
Gait recognition aims to identify individuals by distinguishing unique walking patterns based on video-level pedestrian silhouettes.Previous studies have focused on designing powerful feature extractors to model the s...Gait recognition aims to identify individuals by distinguishing unique walking patterns based on video-level pedestrian silhouettes.Previous studies have focused on designing powerful feature extractors to model the spatio-temporal dependencies of gait,thereby obtaining gait features that contain rich semantic information.However,they have overlooked the potential of feature maps to construct discriminative gait embeddings.In this work,we propose a novel model,EmbedGait,which is designed to learn salient gait embeddings for improved recognition results.Specifically,our framework starts with a frame-level spatial alignment to maintain inter-sequence consistency.Then,horizontal salient mapping(HSM)module is designed to extract the representative embeddings and discard the background information by a designed pooling operation.The subsequent adaptive embedding weighting(AEW)module is used to adaptively highlight the salient embeddings of different body parts and channels.Extensive experiments on the Gait3D,GREW and SUSTech1K datasets demonstrate that our approach improves comparable performance in several benchmarks tests.For example,our proposed EmbedGait achieves rank-1 accuracies of 77.3%,79.0%and 79.6%on Gait3D,GREW and SUSTech1K,respectively.展开更多
We establish an explicit embedding of a quantum affine sl_(n) into a quantum affine sl_(n)+1.This embedding serves as a common generalization of two natural,but seemingly unrelated,embed-dings,one on the quantum affin...We establish an explicit embedding of a quantum affine sl_(n) into a quantum affine sl_(n)+1.This embedding serves as a common generalization of two natural,but seemingly unrelated,embed-dings,one on the quantum affine Schur algebra level and the other on the non-quantum level.The embedding on the quantum affine Schur algebras is used extensively in the analysis of canonical bases of quantum affine sln and gl_(n).The embedding on the non-quantum level is used crucially in a work of Riche and Williamson on the study of modular representation theory of general linear groups over a finite field.The same embedding is also used in a work of Maksimau on the categorical representations of affine general linear algebras.We further provide a more natural compatibility statement of the em-bedding on the idempotent version with that on the quantum affine Schur algebra level.A gl_(n)-variant of the embedding is also established.展开更多
The article “Time-series embeddings from language models: A tool for wind direction nowcasting”, written by Décio ALVES, Fábio MENDON?A, Sheikh Shanawaz MOSTAFA, and Fernando MORGADO-DIAS was originally pu...The article “Time-series embeddings from language models: A tool for wind direction nowcasting”, written by Décio ALVES, Fábio MENDON?A, Sheikh Shanawaz MOSTAFA, and Fernando MORGADO-DIAS was originally published electronically on the publisher's internet portal on 9 July 2024 without open access.展开更多
A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehens...A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.展开更多
文摘The increasing fluency of advanced language models,such as GPT-3.5,GPT-4,and the recently introduced DeepSeek,challenges the ability to distinguish between human-authored and AI-generated academic writing.This situation is raising significant concerns regarding the integrity and authenticity of academic work.In light of the above,the current research evaluates the effectiveness of Bidirectional Long Short-TermMemory(BiLSTM)networks enhanced with pre-trained GloVe(Global Vectors for Word Representation)embeddings to detect AIgenerated scientific Abstracts drawn from the AI-GA(Artificial Intelligence Generated Abstracts)dataset.Two core BiLSTM variants were assessed:a single-layer approach and a dual-layer design,each tested under static or adaptive embeddings.The single-layer model achieved nearly 97%accuracy with trainable GloVe,occasionally surpassing the deeper model.Despite these gains,neither configuration fully matched the 98.7%benchmark set by an earlier LSTMWord2Vec pipeline.Some runs were over-fitted when embeddings were fine-tuned,whereas static embeddings offered a slightly lower yet stable accuracy of around 96%.This lingering gap reinforces a key ethical and procedural concern:relying solely on automated tools,such as Turnitin’s AI-detection features,to penalize individuals’risks and unjust outcomes.Misclassifications,whether legitimate work is misread as AI-generated or engineered text,evade detection,demonstrating that these classifiers should not stand as the sole arbiters of authenticity.Amore comprehensive approach is warranted,one which weaves model outputs into a systematic process supported by expert judgment and institutional guidelines designed to protect originality.
基金funded by Advanced Research Project(30209040702).
文摘Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.
基金Supported by the Grant-in-Aid for Scientific Research(C)by the Japan Society for the Promotion of Science(20K03615)。
文摘Let G be a group.The family of all sets which are closed in every Hausdorf group topology of G form the family of closed sets of a T_(1) topology M_(G) on G called the Markov topology.Similarly,the family of all algebraic subsets of G forms a family of closed sets for another T_(1)topology Z_(G) on G called the Zarski topology.A subgroup H of G is said to be Markov(resp.Zarski)embedded if the equality M_(G|H)=M_(H)(resp.Z_(G|H)=Z_(H))holds.I's proved that an abirary subgroup of a free group is both Zariski and Markov embedded in it.
基金the framework of the program of state support for the centers of the National Technology Initiative(NTI)on the basis of educational institutions of higher education and scientific organizations(Center NTI"Digital Materials Science:New Materials and Substances"on the basis of the Bauman Moscow State Technical University).
文摘Machine learning-assisted prediction of polymer properties prior to synthesis has the potential to significantly accelerate the discovery and development of new polymer materials.To date,several approaches have been implemented to represent the chemical structure in machine learning models,among which Mol2Vec embeddings have attracted considerable attention in the cheminformatics community since their introduction in 2018.However,for small datasets,the use of chemical structure representations typically increases the dimensionality of the input dataset,resulting in a decrease in model performance.Furthermore,the limited diversity of polymer chemical structures hinders the training of reliable embeddings,necessitating complex task-specific architecture implementations.To address these challenges,we examined the efficacy of Mol2Vec pre-trained embeddings in deriving vectorized representations of polymers.This study assesses the impact of incorporating Mol2Vec compound vectors into the input features on the efficacy of a model reliant on the physical properties of 214 polymers.The results will hopefully highlight the potential for improving prediction accuracy in polymer studies by incorporating pre-trained embeddings or promote their utilization when dealing with modestly sized polymer databases.
文摘In this paper,by constructing the current graph of the complete graph K_(12s+9)and a mapping function,we prove that K_(12s+9)(s is an odd number)has at least 6^(2s)×3^(s+3/2) nonisomorphic orientable quadrangular embeddings,and the orientable genus is(12s+9)(12s+4)/8+1.Every one of the nonisomorphic orientable quadrangular embeddings has at least twenty-four 4-edge-colors,and each color appears around each face of orientable quadrangular embeddings.
文摘One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.
文摘随着民航经济的发展和人民生活水平的提高,旅客出行的服务要求越来越高,而当前传统的民航客服知识库检索普遍存在检索准确率以及效率低的问题,已经不能满足旅客的服务需求。文章通过结合Best Match 25算法、文本Embeddings和交叉编码器对知识库进行检索,高效检索出符合座席意图的答案,进而提升民航客服知识库查找效率,缩短座席通话查询时长,提升旅客服务体验,助力实现民航客服数字化、智能化转型。
基金This research was supported by Korea Institute for Advancement of Technology(KIAT)grant funded by the Korea Government(MOTIE)(P0012724,The Competency Development Program for Industry Specialist)and the Soonchunhyang University Research Fund.
文摘The substantial competition among the news industries puts editors under the pressure of posting news articleswhich are likely to gain more user attention. Anticipating the popularity of news articles can help the editorial teamsin making decisions about posting a news article. Article similarity extracted from the articles posted within a smallperiod of time is found to be a useful feature in existing popularity prediction approaches. This work proposesa new approach to estimate the popularity of news articles by adding semantics in the article similarity basedapproach of popularity estimation. A semantically enriched model is proposed which estimates news popularity bymeasuring cosine similarity between document embeddings of the news articles. Word2vec model has been used togenerate distributed representations of the news content. In this work, we define popularity as the number of timesa news article is posted on different websites. We collect data from different websites that post news concerning thedomain of cybersecurity and estimate the popularity of cybersecurity news. The proposed approach is comparedwith different models and it is shown that it outperforms the other models.
文摘The writer identification system identifies individuals based on their handwriting is a frequent topic in biometric authentication and verification systems.Due to its importance,numerous studies have been conducted in various languages.Researchers have established several learning methods for writer identification including supervised and unsupervised learning.However,supervised methods require a large amount of annotation data,which is impossible in most scenarios.On the other hand,unsupervised writer identification methods may be limited and dependent on feature extraction that cannot provide the proper objectives to the architecture and be misinterpreted.This paper introduces an unsupervised writer identification system that analyzes the data and recognizes the writer based on the inter-feature relations of the data to resolve the uncertainty of the features.A pairwise architecturebased Autoembedder was applied to generate clusterable embeddings for handwritten text images.Furthermore,the trained baseline architecture generates the embedding of the data image,and the K-means algorithm is used to distinguish the embedding of individual writers.The proposed model utilized the IAM dataset for the experiment as it is inconsistent with contributions from the authors but is easily accessible for writer identification tasks.In addition,traditional evaluation metrics are used in the proposed model.Finally,the proposed model is compared with a few unsupervised models,and it outperformed the state-of-the-art deep convolutional architectures in recognizing writers based on unlabeled data.
基金supported by the Key R&D Program Project of Zhejiang Province under Grant no.2019 C01004 and 2021C02004.
文摘Purpose:Due to the incompleteness nature of knowledge graphs(KGs),the task of predicting missing links between entities becomes important.Many previous approaches are static,this posed a notable problem that all meanings of a polysemous entity share one embedding vector.This study aims to propose a polysemous embedding approach,named KG embedding under relational contexts(ContE for short),for missing link prediction.Design/methodology/approach:ContE models and infers different relationship patterns by considering the context of the relationship,which is implicit in the local neighborhood of the relationship.The forward and backward impacts of the relationship in ContE are mapped to two different embedding vectors,which represent the contextual information of the relationship.Then,according to the position of the entity,the entity’s polysemous representation is obtained by adding its static embedding vector to the corresponding context vector of the relationship.Findings:ContE is a fully expressive,that is,given any ground truth over the triples,there are embedding assignments to entities and relations that can precisely separate the true triples from false ones.ContE is capable of modeling four connectivity patterns such as symmetry,antisymmetry,inversion and composition.Research limitations:ContE needs to do a grid search to find best parameters to get best performance in practice,which is a time-consuming task.Sometimes,it requires longer entity vectors to get better performance than some other models.Practical implications:ContE is a bilinear model,which is a quite simple model that could be applied to large-scale KGs.By considering contexts of relations,ContE can distinguish the exact meaning of an entity in different triples so that when performing compositional reasoning,it is capable to infer the connectivity patterns of relations and achieves good performance on link prediction tasks.Originality/value:ContE considers the contexts of entities in terms of their positions in triples and the relationships they link to.It decomposes a relation vector into two vectors,namely,forward impact vector and backward impact vector in order to capture the relational contexts.ContE has the same low computational complexity as TransE.Therefore,it provides a new approach for contextualized knowledge graph embedding.
文摘In this paper, the authors discuss the upper bound for the genus of strong embeddings for 3-connected planar graphs on higher surfaces. It is shown that the problem of determining the upper bound for the strong embedding of 3-connected planar near-triangulations on higher non-orientable surfaces is NP-hard. As a corollary, a theorem of Richter, Seymour and Siran about the strong embedding of 3-connected planar graphs is generalized to orientable surface.
文摘In this paper, it is shown that for every maximal planar graph G=(V,E) , a strong embedding on some non orientable surface with genus at most |V(G)|-22 is admitted such that the surface dual of G is also a planar graph. As a corollary, an interpolation theorem for strong embeddings of G on non orientable surfaces is obtained.
文摘The concept of coarse embedding appears in various contexts of geometry,group theory,analysis,and theoretical computer science.The purpose of this paper is to motivate the concept,give an account of its origin,and survey development of the topic.
基金Supported by the NNSF of China(10671073)Supported by the NSF of Jiangsu’s Universities( 07KJB110090)
文摘In this paper we show that the face-width of any embedding of a Halin graph（a type of planar graph） in the torus is one, and give a formula for determining the number of all nonequivalent embeddings of a Halin graph in the torus.
基金partially supported by the German Research Foundation(DFG)(Grant No.Ha 2794/8-1)supported by the China Scholarship Council(CSC)(Grant No.202006350058)partially supported by the Center for Mathematics of the University of Coimbra(funded by the Portuguese Government through FCT/MCTES,DOI 10.54499/UIDB/00324/2020)。
文摘We study embeddings between generalised Triebel–Lizorkin–Morrey spacesε_(ϕ,p,q)^(s)(R^(d))and within the scales of further generalised Morrey smoothness spaces like N_(ϕ,p,q)^(s)(R^(d)),B_(p,q)^(s,ϕ)(R^(d))and F_(p,q)^(s,ϕ)(R^(d)).The latter have been investigated in a recent paper by the first two authors(2023),while the embeddings of the scale N_(ϕ,p,q)^(s)(R^(d))were mainly obtained in a paper of the first and last two authors(2022).Now we concentrate on the characterisation of the spacesε_(ϕ,p,q)^(s)(R^(d)).Our approach requires a wavelet characterisation of those spaces which we establish for the system of Daubechies’wavelets.Then we prove necessary and sufficient conditions for the embeddingε_(ϕ1,p1,q1)^(s1)(R^(d))→ε_(2ϕ2,p2,q2)^(s)(R^(d)).We can also provide some almost final answer to the question whenε_(ϕ,p,q)^(s)(R^(d))is embedded into C(R^(d)),complementing our recent findings in case of N_(ϕ,p,q)^(s)(R^(d)).
文摘Purpose:The paper aims to enhance Arabic machine translation(MT)by proposing novel approaches:(1)a dimensionality reduction technique for word embeddings tailored for Arabic text,optimizing efficiency while retaining semantic information;(2)a comprehensive comparison of meta-embedding techniques to improve translation quality;and(3)a method leveraging self-attention and Gated CNNs to capture token dependencies,including temporal and hierarchical features within sentences,and interactions between different embedding types.These approaches collectively aim to enhance translation quality by combining different embedding schemes and leveraging advanced modeling techniques.Design/methodology/approach:Recent works on MT in general and Arabic MT in particular often pick one type of word embedding model.In this paper,we present a novel approach to enhance Arabic MT by addressing three key aspects.Firstly,we propose a new dimensionality reduction technique for word embeddings,specifically tailored for Arabic text.This technique optimizes the efficiency of embeddings while retaining their semantic information.Secondly,we conduct an extensive comparison of different meta-embedding techniques,exploring the combination of static and contextual embeddings.Through this analysis,we identify the most effective approach to improve translation quality.Lastly,we introduce a novel method that leverages self-attention and Gated convolutional neural networks(CNNs)to capture token dependencies,including temporal and hierarchical features within sentences,as well as interactions between different types of embeddings.Our experimental results demonstrate the effectiveness of our proposed approach in significantly enhancing Arabic MT performance.It outperforms baseline models with a BLEU score increase of 2 points and achieves superior results compared to state-of-the-art approaches,with an average improvement of 4.6 points across all evaluation metrics.Findings:The proposed approaches significantly enhance Arabic MT performance.The dimensionality reduction technique improves the efficiency of word embeddings while preserving semantic information.Comprehensive comparison identifies effective meta-embedding techniques,with the contextualized dynamic meta-embeddings(CDME)model showcasing competitive results.Integration of Gated CNNs with the transformer model surpasses baseline performance,leveraging both architectures’strengths.Overall,these findings demonstrate substantial improvements in translation quality,with a BLEU score increase of 2 points and an average improvement of 4.6 points across all evaluation metrics,outperforming state-of-the-art approaches.Originality/value:The paper’s originality lies in its departure from simply fine-tuning the transformer model for a specific task.Instead,it introduces modifications to the internal architecture of the transformer,integrating Gated CNNs to enhance translation performance.This departure from traditional fine-tuning approaches demonstrates a novel perspective on model enhancement,offering unique insights into improving translation quality without solely relying on pre-existing architectures.The originality in dimensionality reduction lies in the tailored approach for Arabic text.While dimensionality reduction techniques are not new,the paper introduces a specific method optimized for Arabic word embeddings.By employing independent component analysis(ICA)and a post-processing method,the paper effectively reduces the dimensionality of word embeddings while preserving semantic information which has not been investigated before especially for MT task.
基金supported by the International Science and Technology Cooperation Project of Guangzhou Economic and Technological Development District(No.2023GH16).
文摘Gait recognition aims to identify individuals by distinguishing unique walking patterns based on video-level pedestrian silhouettes.Previous studies have focused on designing powerful feature extractors to model the spatio-temporal dependencies of gait,thereby obtaining gait features that contain rich semantic information.However,they have overlooked the potential of feature maps to construct discriminative gait embeddings.In this work,we propose a novel model,EmbedGait,which is designed to learn salient gait embeddings for improved recognition results.Specifically,our framework starts with a frame-level spatial alignment to maintain inter-sequence consistency.Then,horizontal salient mapping(HSM)module is designed to extract the representative embeddings and discard the background information by a designed pooling operation.The subsequent adaptive embedding weighting(AEW)module is used to adaptively highlight the salient embeddings of different body parts and channels.Extensive experiments on the Gait3D,GREW and SUSTech1K datasets demonstrate that our approach improves comparable performance in several benchmarks tests.For example,our proposed EmbedGait achieves rank-1 accuracies of 77.3%,79.0%and 79.6%on Gait3D,GREW and SUSTech1K,respectively.
基金Partially supported by NSF DMS(Grant No.1801915)。
文摘We establish an explicit embedding of a quantum affine sl_(n) into a quantum affine sl_(n)+1.This embedding serves as a common generalization of two natural,but seemingly unrelated,embed-dings,one on the quantum affine Schur algebra level and the other on the non-quantum level.The embedding on the quantum affine Schur algebras is used extensively in the analysis of canonical bases of quantum affine sln and gl_(n).The embedding on the non-quantum level is used crucially in a work of Riche and Williamson on the study of modular representation theory of general linear groups over a finite field.The same embedding is also used in a work of Maksimau on the categorical representations of affine general linear algebras.We further provide a more natural compatibility statement of the em-bedding on the idempotent version with that on the quantum affine Schur algebra level.A gl_(n)-variant of the embedding is also established.
文摘The article “Time-series embeddings from language models: A tool for wind direction nowcasting”, written by Décio ALVES, Fábio MENDON?A, Sheikh Shanawaz MOSTAFA, and Fernando MORGADO-DIAS was originally published electronically on the publisher's internet portal on 9 July 2024 without open access.
文摘A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.
