scholarly journals A Grammar-Based Semantic Similarity Algorithm for Natural Language Sentences

2014 ◽  
Vol 2014 ◽  
pp. 1-17 ◽  
Author(s):  
Ming Che Lee ◽  
Jia Wei Chang ◽  
Tung Cheng Hsieh

This paper presents a grammar and semantic corpus based similarity algorithm for natural language sentences. Natural language, in opposition to “artificial language”, such as computer programming languages, is the language used by the general public for daily communication. Traditional information retrieval approaches, such as vector models, LSA, HAL, or even the ontology-based approaches that extend to include concept similarity comparison instead of cooccurrence terms/words, may not always determine the perfect matching while there is no obvious relation or concept overlap between two natural language sentences. This paper proposes a sentence similarity algorithm that takes advantage of corpus-based ontology and grammatical rules to overcome the addressed problems. Experiments on two famous benchmarks demonstrate that the proposed algorithm has a significant performance improvement in sentences/short-texts with arbitrary syntax and structure.

Author(s):  
Xiaohan Guan ◽  
Jianhui Han ◽  
Zhi Liu ◽  
Mengmeng Zhang

Many tasks of natural language processing such as information retrieval, intelligent question answering, and machine translation require the calculation of sentence similarity. The traditional calculation methods used in the past could not solve semantic understanding problems well. First, the model structure based on Siamese lack of interaction between sentences; second, it has matching problem which contains lacking position information and only using partial matching factor based on the matching model. In this paper, a combination of word and word’s dependence is proposed to calculate the sentence similarity. This combination can extract the word features and word’s dependency features. To extract more matching features, a bi-directional multi-interaction matching sequence model is proposed by using word2vec and dependency2vec. This model obtains matching features by convolving and pooling the word-granularity (word vector, dependency vector) interaction sequences in two directions. Next, the model aggregates the bi-direction matching features. The paper evaluates the model on two tasks: paraphrase identification and natural language inference. The experimental results show that the combination of word and word’s dependence can enhance the ability of extracting matching features between two sentences. The results also show that the model with dependency can achieve higher accuracy than these models without using dependency.


Author(s):  
John Alexander Roberto

Technology-enhanced language learning (TELL) is the result of the evolution of digital language, that is, a special code created by human beings to interact with computers. Digital language has, in turn, allowed for the creation of more specific languages. On the web, TELL is supported by three cross-cultural languages: natural language, visual language, and artificial language. A natural language, such as English or Spanish, becomes cross-cultural when it is processed by automatic means. A visual language is a system of communication using visual elements, such as pictograms. An artificial language, such as programming languages, is designed to communicate instructions to a machine. The author calls this trilogy of languages W3langs. This chapter explores the relationship between TELL and W3langs.


2020 ◽  
Vol 56 (07) ◽  
pp. 40-46
Author(s):  
Khayala Mugamat Mursaliyeva ◽  

The explosion of information and the ever-increasing number of international languages make the modern language situation very difficult. The interaction of languages ultimately leads to the creation of international artificial languages that operate in parallel with the world`s languages. The expansion of interlinguistic issues is a natural consequence of the aggravation of the linguistic landscape of the modern world. The modern interlinguistic dialect, which is defined as a field of linguistics that studies international languages and international languages as a means of communication, deals with the importance of overcoming the barrier.The problem of international artificial languages is widely covered in the writings of I.A.Baudouin de Courtenay, V.P.Qrigorev, N.L.Gudskov, E.K.Drezen, A.D.Dulchenko, M.I.Isayev, S.N.Kuznechov, A.D.Melnikov and many other scientists. Key words:the concept of natural language, the concept of artificial language, the degree of artificiality of language, the authenticity of language


2015 ◽  
Vol 119 (1222) ◽  
pp. 1513-1539 ◽  
Author(s):  
J. W. Lim

AbstractThis design study applied parameterisation to rotor blade for improved performance. In the design, parametric equations were used to represent blade planform changes over the existing rotor blade model. Design variables included blade twist, sweep, dihedral, and radial control point. Updates to the blade structural properties with changes in the design variables allowed accurate evaluation of performance objectives and realistic structural constraints – blade stability, steady moments (flap bending, chord bending, and torsion), and the high g manoeuvring pitch link loads. Performance improvement was demonstrated with multiple parametric designs. Using a parametric design with advanced aerofoils, the predicted power reduction was 1·0% in hover, 10·0% at μ = 0·30, and 17·0% at μ = 0·40 relative to the baseline UH-60A rotor, but these were obtained with a 35% increase in the steady chord bending moment at μ = 0·30 and a 20% increase in the half peak-to-peak pitch link load during the UH-60A UTTAS manoeuvre Low vibration was maintained for this design. More rigorous design efforts, such as chord tapering and/or structural redesign of the blade cross section, would enlarge the feasible design space and likely provide significant performance improvement.


GigaScience ◽  
2018 ◽  
Vol 7 (6) ◽  
Author(s):  
Xiaobo Sun ◽  
Jingjing Gao ◽  
Peng Jin ◽  
Celeste Eng ◽  
Esteban G Burchard ◽  
...  

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Jinqing Hao ◽  
Bingchen Han

Abstract In the discretely amplified transmission systems with erbium-doped fiber amplifiers, the system performance of nonlinearity-compensated optical transmission based on pre-dispersed spectral inversion (PSI) is investigated numerically. We find that PSI offers more significant performance improvement in dispersion-managed (DM) links than that in non-dispersion-managed (noDM) links. On the other hand, the DM link is more sensitive to the span offset from the center of the transmission link than noDM link. The performance difference between DM and noDM links is 1 dB if the span offset equals four spans in 20 × 90 km nonlinear transmission. Furthermore, we show that for the dispersion-managed transmission, in order to obtain the best system performance, the amount of pre-dispersion of the PSI, should be optimized over different dispersion maps.


Author(s):  
Ramon Amela ◽  
Cristian Ramon-Cortes ◽  
Jorge Ejarque ◽  
Javier Conejero ◽  
Rosa M. Badia

Python is a popular programming language due to the simplicity of its syntax, while still achieving a good performance even being an interpreted language. The adoption from multiple scientific communities has evolved in the emergence of a large number of libraries and modules, which has helped to put Python on the top of the list of the programming languages [1]. Task-based programming has been proposed in the recent years as an alternative parallel programming model. PyCOMPSs follows such approach for Python, and this paper presents its extensions to combine task-based parallelism and thread-level parallelism. Also, we present how PyCOMPSs has been adapted to support heterogeneous architectures, including Xeon Phi and GPUs. Results obtained with linear algebra benchmarks demonstrate that significant performance can be obtained with a few lines of Python.


Author(s):  
Ahmed Abbache ◽  
Farid Meziane ◽  
Ghalem Belalem ◽  
Fatma Zohra Belkredim

Query expansion is the process of adding additional relevant terms to the original queries to improve the performance of information retrieval systems. However, previous studies showed that automatic query expansion using WordNet do not lead to an improvement in the performance. One of the main challenges of query expansion is the selection of appropriate terms. In this paper, the authors review this problem using Arabic WordNet and Association Rules within the context of Arabic Language. The results obtained confirmed that with an appropriate selection method, the authors are able to exploit Arabic WordNet to improve the retrieval performance. Their empirical results on a sub-corpus from the Xinhua collection showed that their automatic selection method has achieved a significant performance improvement in terms of MAP and recall and a better precision with the first top retrieved documents.


Sign in / Sign up

Export Citation Format

Share Document