A New Model to Compute Semantic Similarity from Multi-ontology

2013 ◽  
pp. 1-10 ◽  
Author(s):  
Lan Wang ◽  
Ming Chen
Keyword(s):  
Semantic Similarity ◽  
New Model

scholarly journals DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers

2021 ◽  
Author(s):  
Abdul Wahab ◽  
Rafet Sifa
Keyword(s):  
Natural Language ◽  
Sentiment Analysis ◽  
Semantic Similarity ◽  
Syntactic Structure ◽  
Language Modeling ◽  
Benchmark Dataset ◽  
Fine Tuning ◽  
New Model ◽  
Dependency Tree ◽  
Better Than

<div> <div> <div> <p> </p><div> <div> <div> <p>In this paper, we propose a new model named DIBERT which stands for Dependency Injected Bidirectional Encoder Representations from Transformers. DIBERT is a variation of the BERT and has an additional third objective called Parent Prediction (PP) apart from Masked Language Modeling (MLM) and Next Sentence Prediction (NSP). PP injects the syntactic structure of a dependency tree while pre-training the DIBERT which generates syntax-aware generic representations. We use the WikiText-103 benchmark dataset to pre-train both BERT- Base and DIBERT. After fine-tuning, we observe that DIBERT performs better than BERT-Base on various downstream tasks including Semantic Similarity, Natural Language Inference and Sentiment Analysis. </p> </div> </div> </div> </div> </div> </div>

scholarly journals DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers

2021 ◽  
Author(s):  
Abdul Wahab ◽  
Rafet Sifa
Keyword(s):  
Natural Language ◽  
Sentiment Analysis ◽  
Semantic Similarity ◽  
Syntactic Structure ◽  
Language Modeling ◽  
Benchmark Dataset ◽  
Fine Tuning ◽  
New Model ◽  
Dependency Tree ◽  
Better Than

<div> <div> <div> <p> </p><div> <div> <div> <p>In this paper, we propose a new model named DIBERT which stands for Dependency Injected Bidirectional Encoder Representations from Transformers. DIBERT is a variation of the BERT and has an additional third objective called Parent Prediction (PP) apart from Masked Language Modeling (MLM) and Next Sentence Prediction (NSP). PP injects the syntactic structure of a dependency tree while pre-training the DIBERT which generates syntax-aware generic representations. We use the WikiText-103 benchmark dataset to pre-train both BERT- Base and DIBERT. After fine-tuning, we observe that DIBERT performs better than BERT-Base on various downstream tasks including Semantic Similarity, Natural Language Inference and Sentiment Analysis. </p> </div> </div> </div> </div> </div> </div>

An Approach of Web Service Discovery and Composition Based on Logic Petri Nets

2012 ◽  
Vol 605-607 ◽  
pp. 2351-2357 ◽  
Author(s):  
Shi Yang Deng ◽  
Yu Yue Du
Keyword(s):  
Petri Nets ◽  
Web Service ◽  
Semantic Similarity ◽  
Service Discovery ◽  
Logical Inference ◽  
New Model ◽  
Web Service Discovery ◽  
Parameter Matching

A new model is proposed based on logic Petri nets for web service clusters. The service parameters of a cluster are unified and logical expressions are introduced to represent the indeterminacy of service clusters. A service cluster can be used as an integrated unit and parameter matching can be decided based on semantic similarity and logical inference in a service cluster. Some algorithms of web service discovery and composition are given based on logic Petri nets, and the redundant services are removed from service compositions by a backward method. The availability and efficiency of the proposed approach are illustrated by the experiments with large repositories of different sizes.

A New Model to Compute the Information Content of Concepts from Taxonomic Knowledge

2012 ◽  
Vol 8 (2) ◽  
pp. 34-50 ◽  
Author(s):  
David Sánchez ◽  
Montserrat Batet
Keyword(s):  
Information Content ◽  
Semantic Similarity ◽  
Similarity Measures ◽  
New Model ◽  
Amount Of Information ◽  
Data Sparseness ◽  
The Past

The Information Content (IC) of a concept quantifies the amount of information it provides when appearing in a context. In the past, IC used to be computed as a function of concept appearance probabilities in corpora, but corpora-dependency and data sparseness hampered results. Recently, some other authors tried to overcome previous approaches, estimating IC from the knowledge modeled in an ontology. In this paper, the authors develop this idea, by proposing a new model to compute the IC of a concept exploiting the taxonomic knowledge modeled in an ontology. In comparison with related works, their proposal aims to better capture semantic evidences found in the ontology. To test the authors’ approach, they have applied it to well-known semantic similarity measures, which were evaluated using standard benchmarks. Results show that the use of the authors’ model produces, in most cases, more accurate similarity estimations than related works.

A novel model for semantic similarity measurement based on wordnet and word embedding

2021 ◽  
pp. 1-12
Author(s):  
Fuqiang Zhao ◽  
Zhengyu Zhu ◽  
Ping Han
Keyword(s):  
Vector Space ◽  
Semantic Similarity ◽  
Semantic Information ◽  
Word Embedding ◽  
Similarity Measurement ◽  
New Model ◽  
Part Of Speech ◽  
Benchmark Datasets ◽  
Semantic Similarity Measurement ◽  
Novel Model

To measure semantic similarity between words, a novel model DFRVec that encodes multiple semantic information of a word in WordNet into a vector space is presented in this paper. Firstly, three different sub-models are proposed: 1) DefVec: encoding the definitions of a word in WordNet; 2) FormVec: encoding the part-of-speech (POS) of a word in WordNet; 3) RelVec: encoding the relations of a word in WordNet. Then by combining the three sub-models with an existing word embedding, the new model for generating the vector of a word is proposed. Finally, based on DFRVec and the path information in WordNet, a new method DFRVec+Path to measure semantic similarity between words is presented. The experiments on ten benchmark datasets show that DFRVec+Path can outperform many existing methods on semantic similarity measurement.

scholarly journals DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers

2021 ◽  
Author(s):  
Abdul Wahab ◽  
Rafet Sifa
Keyword(s):  
Natural Language ◽  
Sentiment Analysis ◽  
Semantic Similarity ◽  
Syntactic Structure ◽  
Language Modeling ◽  
Benchmark Dataset ◽  
Fine Tuning ◽  
New Model ◽  
Dependency Tree ◽  
Better Than

<div> <div> <div> <p> </p><div> <div> <div> <p>In this paper, we propose a new model named DIBERT which stands for Dependency Injected Bidirectional Encoder Representations from Transformers. DIBERT is a variation of the BERT and has an additional third objective called Parent Prediction (PP) apart from Masked Language Modeling (MLM) and Next Sentence Prediction (NSP). PP injects the syntactic structure of a dependency tree while pre-training the DIBERT which generates syntax-aware generic representations. We use the WikiText-103 benchmark dataset to pre-train both BERT- Base and DIBERT. After fine-tuning, we observe that DIBERT performs better than BERT-Base on various downstream tasks including Semantic Similarity, Natural Language Inference and Sentiment Analysis. </p> </div> </div> </div> </div> </div> </div>

The Hitachi Model HS-8 Electron Microscope

1967 ◽  
Vol 25 ◽  
pp. 238-239
Author(s):  
H. Akabori ◽  
K. Nishiwaki ◽  
K. Yoneta
Keyword(s):  
Electron Microscope ◽  
New Model ◽  
Predecessor Model

By improving the predecessor Model HS- 7 electron microscope for the purpose of easier operation, we have recently completed new Model HS-8 electron microscope featuring higher performance and ease of operation.

Sign in / Sign up

Export Citation Format

Share Document