Deep Feature Fusion Model for Sentence Semantic Matching

Sentence semantic matching(SSM)is a fundamental research in solving natural language processing tasks such as question answering and machine translation.The latest SSM research benefits from deep learning techniques by incorporating attention mechanism to semantically match given sentences.However,how to fully capture the semantic context without losing significant features for sentence encoding is still a challenge.To address this challenge,we propose a deep feature fusion model and integrate it into the most popular deep learning architecture for sentence matching task.The integrated architecture mainly consists of embedding layer,deep feature fusion layer,matching layer and prediction layer.In addition,we also compare the commonly used loss function,and propose a novel hybrid loss function integrating MSE and cross entropy together,considering confidence interval and threshold setting to preserve the indistinguishable instances in training process.To evaluate our model performance,we experiment on two real world public data sets:LCQMC and Quora.The experiment results demonstrate that our model outperforms the most existing advanced deep learning models for sentence matching,benefited from our enhanced loss function and deep feature fusion model for capturing semantic context.

AN IMPROVED HYBRID SEMANTIC MATCHING ALGORITHM WITH LEXICAL SIMILARITY

In this paper, we proposed an improved hybrid semantic matching algorithm combining Input/Output (I/O) semantic matching with text lexical similarity to overcome the disadvantage that the existing semantic matching algorithms were unable to distinguish those services with the same I/O by only performing I/O based service signature matching in semantic web service discovery techniques. The improved algorithm consists of two steps, the first is logic based I/O concept ontology matching, through which the candidate service set is obtained and the second is the service name matching with lexical similarity against the candidate service set, through which the final precise matching result is concluded. Using Ontology Web Language for Services (OWL-S) test collection, we tested our hybrid algorithm and compared it with OWL-S Matchmaker-X (OWLS-MX), the experimental results have shown that the proposed algorithm could pick out the most suitable advertised service corresponding to user's request from very similar ones and provide better matching precision and efficiency than OWLS-MX.

Enhancing Cross-Lingual Image Description: A Multimodal Approach for Semantic Relevance and Stylistic Alignment

Cross-lingual image description,the task of generating image captions in a target language from images and descriptions in a source language,is addressed in this study through a novel approach that combines neural network models and semantic matching techniques.Experiments conducted on the Flickr8k and AraImg2k benchmark datasets,featuring images and descriptions in English and Arabic,showcase remarkable performance improvements over state-of-the-art methods.Our model,equipped with the Image&Cross-Language Semantic Matching module and the Target Language Domain Evaluation module,significantly enhances the semantic relevance of generated image descriptions.For English-to-Arabic and Arabic-to-English cross-language image descriptions,our approach achieves a CIDEr score for English and Arabic of 87.9%and 81.7%,respectively,emphasizing the substantial contributions of our methodology.Comparative analyses with previous works further affirm the superior performance of our approach,and visual results underscore that our model generates image captions that are both semantically accurate and stylistically consistent with the target language.In summary,this study advances the field of cross-lingual image description,offering an effective solution for generating image captions across languages,with the potential to impact multilingual communication and accessibility.Future research directions include expanding to more languages and incorporating diverse visual and textual data sources.

Image Captioning with multi-level similarity-guided semantic matching

Image Captioning is a cross-modal task that needs to automatically generate coherent natural sentences to describe the image contents.Due to the large gap between vision and language modalities,most of the existing methods have the problem of inaccurate semantic matching between images and generated captions.To solve the problem,this paper proposes a novel multi-level similarity-guided semantic matching method for image captioning,which can fuse local and global semantic similarities to learn the latent semantic correlation between images and generated captions.Specifically,we extract the semantic units containing fine-grained semantic information of images and generated captions,respectively.Based on the comparison of the semantic units,we design a local semantic similarity evaluation mechanism.Meanwhile,we employ the CIDEr score to characterize the global semantic similarity.The local and global two-level similarities are finally fused using the reinforcement learning theory,to guide the model optimization to obtain better semantic matching.The quantitative and qualitative experiments on large-scale MSCOCO dataset illustrate the superiority of the proposed method,which can achieve fine-grained semantic matching of images and generated captions.

A sketch-based semantic retrieval approach for 3D CAD models

During the new product development process, reusing the existing CAD models could avoid designing from scratch and decrease human cost. With the advent of big data,how to rapidly and efficiently find out suitable 3D CAD models for design reuse is taken more attention. Currently the sketch-based retrieval approach makes search more convenient, but its accuracy is not high enough; on the other hand, the semantic-based retrieval approach fully utilizes high level semantic information, and makes search much closer to engineers＇ intent.However, effectively extracting and representing semantic information from data sets is difficult.Aiming at these problems, we proposed a sketch-based semantic retrieval approach for reusing3 D CAD models. Firstly a fine granularity semantic descriptor is designed for representing 3D CAD models; Secondly, several heuristic rules are adopted to recognize 3D features from 2D sketch, and the correspondences between 3D feature and 2D loops are built; Finally, semantic and shape similarity measurements are combined together to match the input sketch to 3D CAD models. Hence the retrieval accuracy is improved. A sketch-based prototype system is developed.Experimental results validate the feasibility and effectiveness of our proposed approach.

ACLSTM:A Novel Method for CQA Answer Quality Prediction Based on Question-Answer Joint Learning

Given the limitations of the community question answering(CQA)answer quality prediction method in measuring the semantic information of the answer text,this paper proposes an answer quality prediction model based on the question-answer joint learning(ACLSTM).The attention mechanism is used to obtain the dependency relationship between the Question-and-Answer(Q&A)pairs.Convolutional Neural Network(CNN)and Long Short-term Memory Network(LSTM)are used to extract semantic features of Q&A pairs and calculate their matching degree.Besides,answer semantic representation is combined with other effective extended features as the input representation of the fully connected layer.Compared with other quality prediction models,the ACLSTM model can effectively improve the prediction effect of answer quality.In particular,the mediumquality answer prediction,and its prediction effect is improved after adding effective extended features.Experiments prove that after the ACLSTM model learning,the Q&A pairs can better measure the semantic match between each other,fully reflecting the model’s superior performance in the semantic information processing of the answer text.

Development of a Smart Technique for Mobile Web Services Discovery

Web service(WS)presents a good solution to the interoperability of different types of systems that aims to reduce the overhead of high processing in a resource-limited environment.With the increasing demand for mobile WS(MWS),the WS discovery process has become a significant challenging point in the WS lifecycle that aims to identify the relevant MWSs that best match the service requests.This discovery process is a resource-consuming task that cannot be performed efficiently in a mobile computing environment due to the limitations of mobile devices.Meanwhile,a cloud computing can provide rich computing resources for mobile environments given its unlimited and easily scalable resources.This paper proposes a semantic WS discovery and invocation framework in mobile environments based on cloud and a relationship-aware matchmaking algorithm.The discovery algorithm enriches MWS and user requests semantically with the functional and non-functional properties of Ontology Web Language for Services,such as Quality of Web Service,device context,and user preferences.The WS repository is filtered based on logical reasoning and a parameter-based matching algorithm to minimize the matching space and improve runtime performance.The cosine similarity between the user request and services repository is then assessed to generate the most relevant WS.The relationships among concepts in the ontology are considered to improve the recall and precision ratio.After the WS discovery process,users can invoke and test these services in a mobile environment through a dynamic user interface.The interface of the invocation process is changed according to the WS description document.An application prototype is also developed to evaluate the framework based on a Cordova cross-mobile development framework.

Content-Based Hybrid Deep Neural Network Citation Recommendation Method

The rapid growth of scientific papers makes it difficult to query related papers efficiently,accurately and with high coverage.Traditional citation recommendation algorithms rely heavily on the metadata of query documents,which leads to the low quality of recommendation results.In this paper,DeepCite,a content-based hybrid neural network citation recommendation method is proposed.First,the BERT model was used to extract the high-level semantic representation vectors in the text,then the multi-scale CNN model and BiLSTM model were used to obtain the local information and the sequence information of the context in the sentence,and the text vectors were matched in depth to generate candidate sets.Further,the depth neural network was used to rerank the candidate sets by combining the score of candidate sets and multisource features.In the reranking stage,a variety of Metapath features were extracted from the citation network,and added to the deep neural network to learn,and the ranking of recommendation results were optimized.Compared with PWFC,ClusCite,BM25,RW,NNRank models,the results of the Deepcite algorithm presented in the ANN datasets show that the precision(P@20),recall rate(R@20),MRR and MAP indexesrise by 2.3%,3.9%,2.4%and 2.1%respectively.Experimental results on DBLP datasets show that the improvement is 2.4%,4.3%,1.8%and 1.2%respectively.Therefore,the algorithm proposed in this paper effectively improves the quality of citation recommendation.