Search results for: natural language interfaces

Authors: Aliyu Isah Agaie, Masrah Azrifah Azmi Murad, Nurfadhlina Mohd Sharef, Aida Mustapha

Abstract:

Natural Language Interfaces typically support a restricted language and also have scopes and limitations that naïve users are unaware of, resulting in errors when the users attempt to retrieve information from ontologies. To overcome this challenge, an auto-suggest feature is introduced into the querying process where users are guided through the querying process using interactive query construction system. Guiding users to formulate their queries, while providing them with an unconstrained (or almost unconstrained) way to query the ontology results in better interpretation of the query and ultimately lead to an effective search. The approach described in this paper is unobtrusive and subtly guides the users, so that they have a choice of either selecting from the suggestion list or typing in full. The user is not coerced into accepting system suggestions and can express himself using fragments or full sentences.

Keywords: auto-suggest, expressiveness, habitability, natural language interface, query interpretation, user guidance

Procedia PDF Downloads 445

Authors: Alexander Wachtel, Michael T. Franzen, Walter F. Tichy

Abstract:

Programming requires years of training. With natural language and end user development methods, programming could become available to everyone. It enables end users to program their own devices and extend the functionality of the existing system without any knowledge of programming languages. In this paper, we describe an Interactive Spreadsheet Processing Module (ISPM), a natural language interface to spreadsheets that allows users to address ranges within the spreadsheet based on inferred table schema. Using the ISPM, end users are able to search for values in the schema of the table and to address the data in spreadsheets implicitly. Furthermore, it enables them to select and sort the spreadsheet data by using natural language. ISPM uses a machine learning technique to automatically infer areas within a spreadsheet, including different kinds of headers and data ranges. Since ranges can be identified from natural language queries, the end users can query the data using natural language. During the evaluation 12 undergraduate students were asked to perform operations (sum, sort, group and select) using the system and also Excel without ISPM interface, and the time taken for task completion was compared across the two systems. Only for the selection task did users take less time in Excel (since they directly selected the cells using the mouse) than in ISPM, by using natural language for end user software engineering, to overcome the present bottleneck of professional developers.

Keywords: natural language processing, natural language interfaces, human computer interaction, end user development, dialog systems, data recognition, spreadsheet

Procedia PDF Downloads 271

Authors: Amita Barik, Ranjit Prasad Bahadur

Abstract:

We investigate the role of water molecules in 89 protein-RNA complexes taken from the Protein Data Bank. Those with tRNA and single-stranded RNA are less hydrated than with duplex or ribosomal proteins. Protein-RNA interfaces are hydrated less than protein-DNA interfaces, but more than protein-protein interfaces. Majority of the waters at protein-RNA interfaces makes multiple H-bonds; however, a fraction does not make any. Those making Hbonds have preferences for the polar groups of RNA than its partner protein. The spatial distribution of waters makes interfaces with ribosomal proteins and single-stranded RNA relatively ‘dry’ than interfaces with tRNA and duplex RNA. In contrast to protein-DNA interfaces, mainly due to the presence of the 2’OH, the ribose in protein-RNA interfaces is hydrated more than the phosphate or the bases. The minor groove in protein-RNA interfaces is hydrated more than the major groove, while in protein-DNA interfaces it is reverse. The strands make the highest number of water-mediated H-bonds per unit interface area followed by the helices and the non-regular structures. The preserved waters at protein-RNA interfaces make higher number of H-bonds than the other waters. Preserved waters contribute toward the affinity in protein-RNA recognition and should be carefully treated while engineering protein-RNA interfaces.

Keywords: h-bonds, minor-major grooves, preserved water, protein-RNA interfaces

Procedia PDF Downloads 254

Authors: Xinyu Gong, Zhilin Li, Xintao Liu

Abstract:

Maps are a means of communication. Cartographic language involves established theories of natural language for understanding maps. “Cartographic words’, or “map symbols”, are crucial elements of cartographic language. Personalized mapping is increasingly popular, with growing demands for customized map-making by the general public. Automated symbol-making and customization play a key role in personalized mapping. However, formal representations for the automated construction of map symbols are still lacking. In natural language, the process of word and sentence construction can be formalized. Through the analogy between natural language and graphical language, formal representations of natural language construction can be used as a reference for constructing cartographic language. We selected Chinese character structures (i.e., S

Keywords: personalized mapping, Chinese character, cartographic language, map symbols

Procedia PDF Downloads 136

Authors: Evgeny Pyshkin, Maxim Mozgovoy, Vladislav Volkov

Abstract:

The paper follows a discourse on computer-assisted language learning. We examine problems of foreign language teaching and learning and introduce a metamodel that can be used to define learning models of language grammar structures in order to support teacher/student interaction. Special attention is paid to the concept of a virtual language lab. Our approach to language education assumes to encourage learners to experiment with a language and to learn by discovering patterns of grammatically correct structures created and managed by a language expert.

Keywords: computer-assisted instruction, language learning, natural language grammar models, HCI

Procedia PDF Downloads 472

Authors: Khaled M. Alhawiti

Abstract:

Natural Language Processing (NLP) is an effective approach for bringing improvement in educational setting. This involves initiating the process of learning through the natural acquisition in the educational systems. It is based on following effective approaches for providing the solution for various problems and issues in education. Natural Language Processing provides solution in a variety of different fields associated with the social and cultural context of language learning. It is based on involving various tools and techniques such as grammar, syntax, and structure of text. It is effective approach for teachers, students, authors, and educators for providing assistance for writing, analysis, and assessment procedure. Natural Language Processing is widely integrated in the large number of educational contexts such as research, science, linguistics, e-learning, evaluations system, and various other educational settings such as schools, higher education system, and universities. Natural Language Processing is based on applying scientific approach in the educational settings. In the educational settings, NLP is an effective approach to ensure that students can learn easily in the same way as they acquired language in the natural settings.

Keywords: natural language processing, education, application, e-learning, scientific studies, educational system

Procedia PDF Downloads 465

Authors: Dalila Souilem, Salma Boumiza, Abdelkarim Abdelkader

Abstract:

The Clarifier Dialogue Interface (CDI) is a part of an online teaching system based on human-machine communication in learning situation. This interface used in the system during the learning action specifically in the evaluation step, to clarify ambiguities in the learner's response. The CDI can generate patterns allowing access to an information system, using the selectors associated with lexical units. To instantiate these patterns, the user request (especially learner’s response), must be analyzed and interpreted to deduce the canonical form, the semantic form and the subject of the sentence. For the efficiency of this interface at the interpretation level, a set of substitution operators is carried out in order to extend the possibilities of manipulation with a natural language. A second approach that will be presented in this paper focuses on the object languages with new prospects such as combination of natural language with techniques of handling information system in the area of online education. So all operators, the CDI and other interfaces associated to the domain expertise and teaching strategies will be unified using FRAME representation form.

Keywords: dialogue, e-learning, FRAME, information system, natural language

Procedia PDF Downloads 334

Authors: Khaled M. Alhawiti

Abstract:

This paper aims to analyze the role of natural language processing (NLP). The paper will discuss the role in the context of automated data retrieval, automated question answer, and text structuring. NLP techniques are gaining wider acceptance in real life applications and industrial concerns. There are various complexities involved in processing the text of natural language that could satisfy the need of decision makers. This paper begins with the description of the qualities of NLP practices. The paper then focuses on the challenges in natural language processing. The paper also discusses major techniques of NLP. The last section describes opportunities and challenges for future research.

Keywords: data retrieval, information retrieval, natural language processing, text structuring

Procedia PDF Downloads 303

Authors: Abdulnasser S. Saleh

Abstract:

The importance of metal-semiconductor interfaces comes from the fact that most electronic devices are interconnected using metallic wiring that forms metal–semiconductor contacts. The properties of these contacts can vary considerably depending on the nature of the interface with the semiconductor. Variable-energy positron annihilation spectroscopy has been applied to study interfaces in Al/Si, Au/Si, and Au/GaAs structures. A computational modeling by ROYPROF program is used to analyze Doppler broadening results in order to determine kinds of regions that positrons are likely to sample. In all fittings, the interfaces are found 1 nm thick and act as an absorbing sink for positrons diffusing towards them and may be regarded as highly defective. Internal electric fields were found to influence positrons diffusing to the interfaces and unable to force them cross to the other side. The materials positron affinities are considered in understanding such motion. The results of these theoretical fittings have clearly demonstrated the sensitivity of interfaces in any fitting attempts of analyzing positron spectroscopy data and gave valuable information about metal-semiconductor interfaces.

Keywords: interfaces, semiconductor, positron, defects

Procedia PDF Downloads 225

Authors: Khaled M. Alhawiti

Abstract:

This paper investigates the future of medicine and the use of Natural language processing. The importance of having correct clinical information available online is remarkable; improving patient care at affordable costs could be achieved using automated applications to use the online clinical information. The major challenge towards the retrieval of such vital information is to have it appropriately coded. Majority of the online patient reports are not found to be coded and not accessible as its recorded in natural language text. The use of Natural Language processing provides a feasible solution by retrieving and organizing clinical information, available in text and transforming clinical data that is available for use. Systems used in NLP are rather complex to construct, as they entail considerable knowledge, however significant development has been made. Newly formed NLP systems have been tested and have established performance that is promising and considered as practical clinical applications.

Keywords: clinical information, information retrieval, natural language processing, automated applications

Procedia PDF Downloads 371

Authors: Moquan Gong

Abstract:

In recent years, with the rapid development of deep learning, pre-training technology for natural language processing has made great progress. The early field of natural language processing has long used word vector methods such as Word2Vec to encode text. These word vector methods can also be regarded as static pre-training techniques. However, this context-free text representation brings very limited improvement to subsequent natural language processing tasks and cannot solve the problem of word polysemy. ELMo proposes a context-sensitive text representation method that can effectively handle polysemy problems. Since then, pre-training language models such as GPT and BERT have been proposed one after another. Among them, the BERT model has significantly improved its performance on many typical downstream tasks, greatly promoting the technological development in the field of natural language processing, and has since entered the field of natural language processing. The era of dynamic pre-training technology. Since then, a large number of pre-trained language models based on BERT and XLNet have continued to emerge, and pre-training technology has become an indispensable mainstream technology in the field of natural language processing. This article first gives an overview of pre-training technology and its development history, and introduces in detail the classic pre-training technology in the field of natural language processing, including early static pre-training technology and classic dynamic pre-training technology; and then briefly sorts out a series of enlightening technologies. Pre-training technology, including improved models based on BERT and XLNet; on this basis, analyze the problems faced by current pre-training technology research; finally, look forward to the future development trend of pre-training technology.

Keywords: natural language processing, pre-training, language model, word vectors

Procedia PDF Downloads 11

Authors: Tao Qu, Chandra Prakash, Vikas Tomar

Abstract:

The interfaces between organic and inorganic phases in natural materials have been shown to be a key factor contributing to their high performance. This work analyzes crack propagation in a 2-ply laminate subjected to uniaxial tensile mode-I crack propagation loading that has laminate properties derived based on biological material constituents (marine exoskeleton- chitin and calcite). Interfaces in such laminates are explicitly modeled based on earlier molecular simulations performed by authors. Extended finite element method and cohesive zone modeling based simulations coupled with theoretical analysis are used to analyze crack propagation. Analyses explicitly quantify the effect that interface mechanical property variation has on the delamination as well as the transverse crack propagation in examined 2-ply laminates.

Keywords: chitin, composites, interfaces, fracture

Procedia PDF Downloads 339

Authors: Khaled M. Alhawiti

Abstract:

Reading capability is a major segment of language competency. On the other hand, discovering topical writings at a fitting level for outside and second language learners is a test for educators. We address this issue utilizing natural language preparing innovation to survey reading level and streamline content. In the connection of outside and second-language learning, existing measures of reading level are not appropriate to this errand. Related work has demonstrated the profit of utilizing measurable language preparing procedures; we expand these thoughts and incorporate other potential peculiarities to measure intelligibility. In the first piece of this examination, we join characteristics from measurable language models, customary reading level measures and other language preparing apparatuses to deliver a finer technique for recognizing reading level. We examine the execution of human annotators and assess results for our finders concerning human appraisals. A key commitment is that our identifiers are trainable; with preparing and test information from the same space, our finders beat more general reading level instruments (Flesch-Kincaid and Lexile). Trainability will permit execution to be tuned to address the needs of specific gatherings or understudies.

Keywords: natural language processing, trainability, syntactic simplification tools, education

Procedia PDF Downloads 449

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 230

Authors: Irene Yi

Abstract:

Machine learning, natural language processing, and neural network models of language are becoming more and more prevalent in the fields of technology and linguistics today. Training data for machines are at best, large corpora of human literature and at worst, a reflection of the ugliness in society. Machines have been trained on millions of human books, only to find that in the course of human history, derogatory and sexist adjectives are used significantly more frequently when describing females in history and literature than when describing males. This is extremely problematic, both as training data, and as the outcome of natural language processing. As machines start to handle more responsibilities, it is crucial to ensure that they do not take with them historical sexist and misogynistic notions. This paper gathers data and algorithms from neural network models of language having to deal with syntax, semantics, sociolinguistics, and text classification. Results are significant in showing the existing intentional and unintentional misogynistic notions used to train machines, as well as in developing better technologies that take into account the semantics and syntax of text to be more mindful and reflect gender equality. Further, this paper deals with the idea of non-binary gender pronouns and how machines can process these pronouns correctly, given its semantic and syntactic context. This paper also delves into the implications of gendered grammar and its effect, cross-linguistically, on natural language processing. Languages such as French or Spanish not only have rigid gendered grammar rules, but also historically patriarchal societies. The progression of society comes hand in hand with not only its language, but how machines process those natural languages. These ideas are all extremely vital to the development of natural language models in technology, and they must be taken into account immediately.

Keywords: gendered grammar, misogynistic language, natural language processing, neural networks

Procedia PDF Downloads 80

Authors: Subodh Chandra Shakya, Rajendra Sapkota, Aakash Tamang, Shushant Pudasaini, Sujan Adhikari, Sajjan Adhikari

Abstract:

Lots of efforts have been made in order to measure the semantic similarity between the text corpora in the documents. Techniques have been evolved to measure the similarity of two documents. One such state-of-art technique in the field of Natural Language Processing (NLP) is word to vector models, which converts the words into their word-embedding and measures the similarity between the vectors. We found this to be quite useful for the task of resume ranking. So, this research paper is the implementation of the word2vec model along with other Natural Language Processing techniques in order to rank the resumes for the particular job description so as to automate the process of hiring. The research paper proposes the system and the findings that were made during the process of building the system.

Keywords: chunking, document similarity, information extraction, natural language processing, word2vec, word embedding

Procedia PDF Downloads 123

Authors: Nor Diana Ahmad, Eric Atwell, Brandon Bennett

Abstract:

Text processing techniques for English have been developed for several decades. But for the Malay language, text processing methods are still far behind. Moreover, there are limited resources, tools for computational linguistic analysis available for the Malay language. Therefore, this research presents the use of natural language processing (NLP) in processing Malay translated Qur’an text. As the result, a new language resource for Malay translated Qur’an was created. This resource will help other researchers to build the necessary processing tools for the Malay language. This research also develops a simple question-answer prototype to demonstrate the use of the Malay Qur’an resource for text processing. This prototype has been developed using Python. The prototype pre-processes the Malay Qur’an and an input query using a stemming algorithm and then searches for occurrences of the query word stem. The result produced shows improved matching likelihood between user query and its answer. A POS-tagging algorithm has also been produced. The stemming and tagging algorithms can be used as tools for research related to other Malay texts and can be used to support applications such as information retrieval, question answering systems, ontology-based search and other text analysis tasks.

Keywords: language resource, Malay translated Qur'an, natural language processing (NLP), text processing

Procedia PDF Downloads 280

Authors: Pingping Lin, Xudong Luo

Abstract:

Natural language often conveys emotions of speakers. Therefore, sentiment analysis on what people say is prevalent in the field of natural language process and has great application value in many practical problems. Thus, to help people understand its application value, in this paper, we survey various applications of sentiment analysis, including the ones in online business and offline business as well as other types of its applications. In particular, we give some application examples in intelligent customer service systems in China. Besides, we compare the applications of sentiment analysis on Twitter, Weibo, Taobao and Facebook, and discuss some challenges. Finally, we point out the challenges faced in the applications of sentiment analysis and the work that is worth being studied in the future.

Keywords: application, natural language processing, online comments, sentiment analysis

Procedia PDF Downloads 220

Authors: Legkikh Victoria

Abstract:

The purpose of keeping bi/multilingualism is usually a way to let the child speak two/three languages at the same level. The main problem which normally appears is a mixed language or a domination of one language. The same level of two or more languages would be ideal but practically not easily reachable. So it was made an experiment with a girl with a natural multilingualism as an attempt to avoid a dominant language in the preschool age. The girl lives in Germany and the main languages for her are Italian, Russian and German but she also hears every day English. ‘One parent – one language’ strategy was used since the beginning so Italian and Russian were spoken to her since her birth, English was spoken between the parents and when she was 1,5 it was added German as a language of a nursery. In order to avoid a dominant language, she was always put in international groups with activity in different languages. Even if it was not possible to avoid an interference of languages in this case we can talk not only about natural multilingualism but also about balanced bilingualism in preschool time. The languages have been developing in parallel with different accents in a different period. Now at the age of 6 we can see natural horizontal multilingualism Russian/Italian/German/English. At the moment, her Russian/Italian bilingualism is balanced. German vocabulary is less but the language is active and English is receptive. We can also see a reciprocal interference of all the three languages (English is receptive so the simple phrases are normally said correctly but they are not enough to judge the level of language interference and it is not noticed any ‘English’ mistakes in other languages). After analysis of the state of every language, we can see as a positive and negative result of the experiment. As a positive result we can see that in the age of 6 the girl does not refuse any language, three languages are active, she differentiate languages and even if she says a word from another language she notifies that it is not a correct word, and the most important are the fact, that she does not have a preferred language. As a prove of the last statement it is to be noticed not only her self-identification as ‘half Russian and half Italian’ but also an answer to the question about her ‘mother tongue’: ‘I do not know, probably, when I have my own children I will speak one day Russian and one day Italian and sometimes German’. As a negative result, we can notice that not only a development of all the three languages are a little bit slower than it is supposed for her age but since she does not have a dominating language she also does not have a ‘perfect’ language and the interference is reciprocal. In any case, the experiment shows that it is possible to keep at least two languages without a preference in a pre-school multilingual space.

Keywords: balanced bilingualism, language interference, natural multilingualism, preschool multilingual education

Procedia PDF Downloads 246

Authors: Inuwa Danladi Bawa

Abstract:

One of the challenges of African states in the development of education in the past and the present is the problem of literacy. Literacy in the first language is seen as a strong base for the development of second language; they are mostly the language of education. Language development is an offshoot of language planning; so the need to develop literacy in both first and second language affects language education and predicts the extent of achievement of the entire education sector. The need to balance literacy acquisition in first language for good conditioning the acquisition of second language is paramount. Likely constraints that includes; non-standardization, underdeveloped and undeveloped first languages are among many. Solutions to some of these include the development of materials and use of the stages and levels of literacy acquisition. This is with believed that a child writes well in second language if he has literacy in the first language.

Keywords: first language, second language, literacy, english language, linguistics

Procedia PDF Downloads 400

Authors: Gal Belsitzman, Rose Stamp, Atay Citron, Wendy Sandler

Abstract:

Sign languages are considered endangered. The vitality of sign languages is compromised by its unique sociolinguistic situation, in which hearing parents that give birth to deaf children usually decide to cochlear implant their child. Therefore, these children don’t acquire their natural language – Sign Language. Despite this, many sign languages, such as Israeli Sign Language (ISL) are thriving. The continued survival of similar languages under threat has been associated with the remarkable resilience of the language community. In particular, deaf literary traditions are central in reminding the community of the importance of the language. One example of a deaf literary tradition which has received increased popularity in recent years is deaf theatre. The Ebisu Sign Language Theatre Laboratory, developed as part of the multidisciplinary Grammar of the Body Research Project, is the first deaf theatre company in Israel. Ebisu Theatre combines physical theatre and sign language research, to allow for a natural laboratory to analyze the creative use of the body. In this presentation, we focus on the recent theatre production called ‘Their language’ which tells of the struggle faced by the deaf community to use their own natural language in the education system. A thorough analysis unravels how linguistic properties are integrated with the use of poetic devices and physical theatre techniques in this performance, enabling wider access by both deaf and hearing audiences, without interpretation. Interviews with the audience illustrate the significance of this art form which serves a dual purpose, both as empowering for the deaf community and educational for the hearing and deaf audiences, by raising awareness of community-related issues.

Keywords: deaf theatre, empowerment, language revitalization, sign language

Procedia PDF Downloads 134

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long short-term memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: dialogue management, response generation, deep learning, evaluation

Procedia PDF Downloads 123

Authors: Abderrahim Siam, Ramdane Maamri, Zaidi Sahnoun

Abstract:

The development of adaptive user interfaces (UI) presents for a long time an important research area in which researcher attempt to call upon the full resources and skills of several disciplines. The adaptive UI community holds a thorough knowledge regarding the adaptation of UIs with users and with contexts of use. Several solutions, models, formalisms, techniques, and mechanisms were proposed to develop adaptive UI. In this paper, we propose an approach based on the fuzzy set theory for modeling the concept of the appropriateness of different solutions of UI adaptation with different situations for which interactive systems have to adapt their UIs.

Keywords: adaptive user interfaces, adaptation solution’s appropriateness, fuzzy sets

Procedia PDF Downloads 446

Authors: Hina Verma, Karine Le Guen, Renaud Dalaunay, Iyas Ismail, Vita Ilakovac, Jean Pascal Rueff, Yunlin Jacques Zheng, Philippe Jonnard

Abstract:

To the extent of our knowledge, X-ray emission spectroscopy (XES) has been applied in the soft x-ray region (photon energy ≤ 2 keV) to study the buried layers and interfaces of stacks of nanometer-thin films. Now we extend the methodology to study the buried interfaces in the hard X-ray region (i.e., ≥ five keV). The emission spectra allow us to study the interactions between elements in the buried layers from the analysis of their valence states, thereby providing sensitive information about the physical-chemical environment of the emitting element in multilayers. We exploit the chemical sensitivity of XES to study the interfaces between Fe and Si layers in the Fe/Si multilayer from the Fe Kβ₂,₅ emission spectra (7108 eV). The Fe Kβ₅ emission line results from the electronic transition from occupied 3d to 1s levels (i.e., valence to core transition) and is hence sensitive to the chemical state of emitting Fe atoms. The comparison of emission spectra recorded for Fe/Si multilayer with Fe and FeSi₂ references reveal the formation of FeSi₂ at the Fe-Si interfaces inside the multilayer stack. The interfacial thickness was calculated to be 1.4 ± 0.2 nm by taking into consideration the intensity of Fe atoms emitted from the interface and the Fe layer. The formation of FeSi₂ at the interface was further confirmed by the X-ray diffraction and X-ray photoelectron spectroscopy done on the Fe/Si multilayer. Hence, we can conclude that the XES in the hard X-ray range could be used to study multilayers and their interfaces and obtain information both qualitatively and quantitatively.

Keywords: buried interfaces, hard X-ray emission spectroscopy, X-ray diffraction, X-ray photoelectron spectroscopy

Procedia PDF Downloads 111

Authors: Zhengrong Wu, Haibo Yang

Abstract:

In the context of escalating global climate change and environmental degradation, the complexity and frequency of natural disasters are continually increasing. Confronted with an abundance of information regarding natural disasters, traditional knowledge graph construction methods, which heavily rely on grammatical rules and prior knowledge, demonstrate suboptimal performance in processing complex, multi-source disaster information. This study, drawing upon past natural disaster reports, disaster-related literature in both English and Chinese, and data from various disaster monitoring stations, constructs question-answer templates based on large language models. Utilizing the P-Tune method, the ChatGLM2-6B model is fine-tuned, leading to the development of a disaster knowledge graph based on large language models. This serves as a knowledge database support for disaster emergency response.

Keywords: large language model, knowledge graph, disaster, deep learning

Procedia PDF Downloads 15

Authors: Amal Alshahrani, Allan Ramsay

Abstract:

Paraphrasing is one of the important tasks in natural language processing; i.e. alternative ways to express the same concept by using different words or phrases. Paraphrases can be used in many natural language applications, such as Information Retrieval, Machine Translation, Question Answering, Text Summarization, or Information Extraction. To obtain pairs of sentences that are paraphrases we create a system that automatically extracts paraphrases from a corpus, which is built from different sources of news article since these are likely to contain paraphrases when they report the same event on the same day. There are existing simple standard approaches (e.g. TF-IDF vector space, cosine similarity) and alignment technique (e.g. Dynamic Time Warping (DTW)) for extracting paraphrase which have been applied to the English. However, the performance of these approaches could be affected when they are applied to another language, for instance Arabic language, due to the presence of phenomena which are not present in English, such as Free Word Order, Zero copula, and Pro-dropping. These phenomena will affect the performance of these algorithms. Thus, if we can analysis how the existing algorithms for English fail for Arabic then we can find a solution for Arabic. The results are promising.

Keywords: natural language processing, TF-IDF, cosine similarity, dynamic time warping (DTW)

Procedia PDF Downloads 349

Authors: Zeineb Ben Azzouz, Wahiba Ben Abdessalem Karaa

Abstract:

The automated extraction of UML class diagram from natural language requirements is a highly challenging task. Many approaches, frameworks and tools have been presented in this field. Nonetheless, the experiments of these tools have shown that there is no approach that can work best all the time. In this context, we propose a new accurate approach to facilitate the automatic mapping from textual requirements to UML class diagram. Our new approach integrates the best properties of statistical Natural Language Processing (NLP) techniques to reduce ambiguity when analysing natural language requirements text. In addition, our approach follows the best practices defined by conceptual modelling experts to determine some patterns indispensable for the extraction of basic elements and concepts of the class diagram. Once the relevant information of class diagram is captured, a XMI document is generated and imported with a CASE tool to build the corresponding UML class diagram.

Keywords: class diagram, user’s requirements, XMI, software engineering

Procedia PDF Downloads 436

Authors: Clarisse Lawson-Guidigbe, Nicolas Louveton, Kahina Amokrane-Ferka, Jean-Marc Andre

Abstract:

Trust in automated driving systems is receiving growing attention in the research community. Anthropomorphism has been identified by past research as a trust-building factor. In this paper, we consider three anthropomorphic interfaces integrating three versions of a virtual assistant. We attempt to measure the impact of each of these interfaces on trust in the automated driving system. An experiment following a between-subject design was conducted in a driving simulator (N = 36) to evaluate participants’ performance and experience in two handover situations (a simple one and a critical one). Perception of anthropomorphism and trust was measured using scales, while participants’ experience was measured during elicitation interviews. We found no significant difference between the three interfaces regarding the perception of anthropomorphism, trust levels, or experience. However, regarding participants’ performance, we found a significant difference between the three interfaces in the simple handover situations but not the critical one. Learnings from anthropomorphism and trust measurement scales are discussed and suggestions for further research are proposed.

Keywords: highly automated driving, trust, anthropomorphic design, mindful anthropomorphism, mindless anthropomorphism

Procedia PDF Downloads 107

Authors: Faezeh Shalchy

Abstract:

Concrete is the most used materials in the world. It is also one of the most versatile while complex materials which human have used for construction. However, concrete is weak in tension, over the past thirty years many studies were accomplished to improve the tensile properties of concrete (cement-based materials) using a variety of methods. One of the most successful attempts is to use polymeric fibers in the structure of concrete to obtain a composite with high tensile strength and ductility. Understanding the mechanical behavior of fiber reinforced concrete requires the knowledge of the fiber/matrix interfaces at the small scale. In this study, a combination of numerical simulations and experimental techniques have been used to study the nano structure of fiber/matrix interfaces. A new model for calcium-silicate-hydrate (C-S-H)/fiber interfaces is proposed based on Scanning Electron Microscopy (SEM) and Energy-dispersive X-ray spectroscopy (EDX) analysis. The adhesion energy between the C-S-H gel and 2 different polymeric fibers (polyvinyl alcohol and polypropylene) was numerically studied at the atomistic level since adhesion is one of the key factors in the design of fiber reinforced composites. The mechanisms of adhesion as a function of the nano structure of fiber/matrix interfaces are also studied and discussed.

Keywords: fiber-reinforced concrete, adhesion, molecular modeling

Procedia PDF Downloads 299

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 59