Search results for: natural language inference

Authors: Mikhail Zarechnev, Bora I. Kumova

Abstract:

A syllogism is a deductive inference scheme used to derive a conclusion from a set of premises. In a categorical syllogisms, there are only two premises and every premise and conclusion is given in form of a quantified relationship between two objects. The different order of objects in premises give classification known as figures. We have shown that the ordered combinations of 3 generalized quantifiers with certain figure provide in total of 108 syllogistic moods which can be considered as different inference rules. The classical syllogistic system allows to model human thought and reasoning with syllogistic structures always attracted the attention of cognitive scientists. Since automated reasoning is considered as part of learning subsystem of AI agents, syllogistic system can be applied for this approach. Another application of syllogistic system is related to inference mechanisms on the Semantic Web applications. In this paper we proposed the mathematical model and algorithm for syllogistic reasoning. Also the model of iterative syllogistic reasoning in case of continuous flows of incoming data based on case–based reasoning and possible applications of proposed system were discussed.

Keywords: categorical syllogism, case-based reasoning, cognitive architecture, inference on the semantic web, syllogistic reasoning

Procedia PDF Downloads 395

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 144

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 31

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 358

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 449

Authors: Jutta Ransmayr

Abstract:

The German language is known to be one of the most varied and diverse languages in Europe. This variance in the standard language can be conceptualized using the pluricentric concept, which has been useful for describing the German language for more than three decades. Up to now, there have hardly been any well-founded studies of how Austrian teachers and pupils conceptualize the German language and how they view the varieties of German and especially Austrian German. The language attitudes and norms of German teachers are of particular interest in the normative, educational language-oriented school context. The teachers’ attitudes are, in turn, formative for the attitudes of the students, especially since Austrian German is an important element in the construction of Austrian national identity. The project 'Austrian German as a Language of Instruction and Education' dealt, among other things, with the attitude of language laypeople (pupils, n = 1253) and language experts (teachers, n = 164) towards the Austrian standard variety. It also aimed to find out to what extent external factors such as regional origin, age, education, or media use to influence these attitudes. It was examined whether language change phenomena can be determined and to what extent language change is in conflict with loyalty to variants. The study also focused on what norms prevail among German teachers, how they deal with standard language variation from a normative point of view, and to what extent they correct exonorm-oriented, as claimed in the literature. Methodologically, both quantitative (questionnaire survey) and qualitative methods were used (interviews with 21 teachers, 2 group discussions, and participatory observation of lessons in 7 school classes). The data were evaluated in terms of inference statistics and discourse analysis. This paper reports on the results of this project.

Keywords: Austrian German, language attitudes and linguistic identity, linguistic loyalty, teachers and students

Procedia PDF Downloads 96

Authors: Sung Hyun Yoo, In Hwan Choi, Jun Ho Jung, Choon Ki Ahn, Myo Taeg Lim

Abstract:

Home energy management system (HEMS) has been issued to reduce the power consumption. The HEMS performs electric power control for the indoor electric device. However, HEMS commonly treats the smart devices. In this paper, we suggest the output estimation of home legacy device using the artificial neural fuzzy inference system (ANFIS). This paper discusses the overview and the architecture of the system. In addition, accurate performance of the output estimation using the ANFIS inference system is shown via a numerical example.

Keywords: artificial neural fuzzy inference system (ANFIS), home energy management system (HEMS), smart device, legacy device

Procedia PDF Downloads 523

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 83

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 458

Authors: Diyah Atiek Mustikawati

Abstract:

Language register refers to a variety of a language used for particular purpose or in a particular social setting. Language register also means as a concept of adapting one’s use of language to conform to standards or tradition in a given professional or social situation. This descriptive study tends to discuss about the form of language register in transportation aspect, factors, also the function of use it. Mostly, language register in transportation aspect uses short sentences in form of informal register. The factor caused language register used are speaker, word choice, background of language. The functions of language register in transportations aspect are to make communication between crew easily, also to keep safety when they were in bad condition. Transportation language register developed naturally as one of variety of language used.

Keywords: language register, language variety, communication, transportation

Procedia PDF Downloads 450

Authors: Md Yeasin, Ranjit Kumar Paul

Abstract:

In recent years, recommendation systems have become indispensable tools for agricultural system. The accurate and timely recommendations can significantly impact crop yield and overall productivity. Causal inference modeling aims to establish cause-and-effect relationships by identifying the impact of variables or factors on outcomes, enabling more accurate and reliable recommendations. New advancements in causal inference models have been found in the literature. With the advent of the modern era, deep learning and machine learning models have emerged as efficient tools for modeling. This study proposed an innovative approach to enhance recommendation systems-based machine learning based casual inference model. By considering the causal effect and opportunity cost of covariates, the proposed system can provide more reliable and actionable recommendations for cereal farmers. To validate the effectiveness of the proposed approach, experiments are conducted using cereal cultivation data of eastern India. Comparative evaluations are performed against existing correlation-based recommendation systems, demonstrating the superiority of the advanced causal inference modeling approach in terms of recommendation accuracy and impact on crop yield. Overall, it empowers farmers with personalized recommendations tailored to their specific circumstances, leading to optimized decision-making and increased crop productivity.

Keywords: agriculture, casual inference, machine learning, recommendation system

Procedia PDF Downloads 62

Authors: Shael Brown, Reza Farivar

Abstract:

Persistence diagrams capture valuable topological features of datasets that other methods cannot uncover. Still, their adoption in data pipelines has been limited due to the lack of publicly available tools in R (and python) for analyzing groups of them with machine learning and statistical inference. In an easy-to-use and scalable R package called TDApplied, we implement several applied analysis methods tailored to groups of persistence diagrams. The two main contributions of our package are comprehensiveness (most functions do not have implementations elsewhere) and speed (shown through benchmarking against other R packages). We demonstrate applications of the tools on simulated data to illustrate how easily practical analyses of any dataset can be enhanced with topological information.

Keywords: machine learning, persistence diagrams, R, statistical inference

Procedia PDF Downloads 57

Authors: Orhun Aydin, Mark V. Janikas, Rodrigo Alves, Renato Assuncao

Abstract:

In this paper, a tree-based perturbation methodology for regionalization inference is presented. Regionalization is a constrained optimization problem that aims to create groups with similar attributes while satisfying spatial contiguity constraints. Similar to any constrained optimization problem, the spatial constraint may hinder convergence to some global minima, resulting in spatially contiguous members of a group with dissimilar attributes. This paper presents a general methodology for rigorously perturbing spatial constraints through the use of random spanning trees. The general framework presented can be used to quantify the effect of the spatial constraints in the overall regionalization result. We compare several types of stochastic spanning trees used in inference problems such as fuzzy regionalization and determining the number of regions. Performance of stochastic spanning trees is juxtaposed against the traditional permutation-based hypothesis testing frequently used in spatial statistics. Inference results for fuzzy regionalization and determining the number of regions is presented on the Local Area Personal Incomes for Texas Counties provided by the Bureau of Economic Analysis.

Keywords: regionalization, constrained clustering, probabilistic inference, fuzzy clustering

Procedia PDF Downloads 203

Authors: Allmin Susaiyah, Aki Härmä, Milan Petković

Abstract:

Automatic generation of insights from data using insight mining systems (IMS) is useful in many applications, such as personal health tracking, patient monitoring, and business process management. Existing IMS face challenges in controlling insight extraction, scaling to large databases, and generalising to unseen domains. In this work, we propose a hybrid approach consisting of rule-based and neural components for generating insights from data while overcoming the aforementioned challenges. Firstly, a rule-based data 2CNL component is used to extract statistically significant insights from data and represent them in a controlled natural language (CNL). Secondly, a BERTSum-based CNL2NL component is used to convert these CNLs into natural language texts. We improve the model using task-specific and domain-specific fine-tuning. Our approach has been evaluated using statistical techniques and standard evaluation metrics. We overcame the aforementioned challenges and observed significant improvement with domain-specific fine-tuning.

Keywords: data mining, insight mining, natural language generation, pre-trained language models

Procedia PDF Downloads 88

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 102

Authors: Mahmudjon Kuchkarov, Marufjon Kuchkarov

Abstract:

The origin of ‘Human Language’ is still a secret and the most interesting subject of historical linguistics. The core element is the nature of labeling or coding the things or processes with symbols and sounds. In this paper, we investigate human’s involuntary Paired Sounds and Shape Production (PSSP) and its contribution to the development of early human communication. Aimed at twenty-six volunteers who provided many physical movements with various difficulties, the research team investigated the natural, repeatable, and paired sounds and shape productions during human activities. The paper claims the involvement of Paired Sounds and Shape Production (PSSP) in the phonetic origin of some modern words and the existence of similarities between elements of PSSP with characters of the classic Latin alphabet. The results may be used not only as a supporting idea for existing theories but to create a closer look at some fundamental nature of the origin of the languages as well.

Keywords: body shape, body language, coding, Latin alphabet, merging method, movement language, movement sound, natural sound, origin of language, pairing, phonetics, sound and shape production, word origin, word semantic

Procedia PDF Downloads 206

Authors: Bastian Haarmann, Likas Sikorski

Abstract:

In this paper, we introduce an NLG application for the automatic creation of ready-to-publish texts from big data. The fully automatic generated stories have a high resemblance to the style in which the human writer would draw up a news story. Topics may include soccer games, stock exchange market reports, weather forecasts and many more. The generation of the texts runs according to the human language production. Each generated text is unique. Ready-to-publish stories written by a computer application can help humans to quickly grasp the outcomes of big data analyses, save time-consuming pre-formulations for journalists and cater to rather small audiences by offering stories that would otherwise not exist.

Keywords: big data, natural language generation, publishing, robotic journalism

Procedia PDF Downloads 410

Authors: Josef Steinberger, Vanni Zavarella, Hristo Tanev

Abstract:

Natural disasters cause tens of thousands of victims and massive material damages. We refer to all those events caused by natural disasters, such as damage on people, infrastructure, vehicles, services and resource supply, as micro events. This paper addresses the problem of micro - event detection in online media sources. We present a natural language grammar learning algorithm and apply it to online news. The algorithm in question is based on distributional clustering and detection of word collocations. We also explore the extraction of micro-events from social media and describe a Twitter mining robot, who uses combinations of keywords to detect tweets which talk about effects of disasters.

Keywords: online news, natural language processing, machine learning, event extraction, crisis computing, disaster effects, Twitter

Procedia PDF Downloads 461

Authors: James Jr. Mashiyane, Risuna Nkolele, Stephanie J. Müller, Gciniwe S. Dlamini, Rebone L. Meraba, Darlington S. Mapiye

Abstract:

When performing language tasks in natural language processing (NLP), the dimensionality of word embeddings is chosen either ad-hoc or is calculated by optimizing the Pairwise Inner Product (PIP) loss. The PIP loss is a metric that measures the dissimilarity between word embeddings, and it is obtained through matrix perturbation theory by utilizing the unitary invariance of word embeddings. Unlike in natural language, in genomics, especially in genome sequence processing, unlike in natural language processing, there is no notion of a “word,” but rather, there are sequence substrings of length k called k-mers. K-mers sizes matter, and they vary depending on the goal of the task at hand. The dimensionality of word embeddings in NLP has been studied using the matrix perturbation theory and the PIP loss. In this paper, the sufficiency and reliability of applying word-embedding algorithms to various genomic sequence datasets are investigated to understand the relationship between the k-mer size and their embedding dimension. This is completed by studying the scaling capability of three embedding algorithms, namely Latent Semantic analysis (LSA), Word2Vec, and Global Vectors (GloVe), with respect to the k-mer size. Utilising the PIP loss as a metric to train embeddings on different datasets, we also show that Word2Vec outperforms LSA and GloVe in accurate computing embeddings as both the k-mer size and vocabulary increase. Finally, the shortcomings of natural language processing embedding algorithms in performing genomic tasks are discussed.

Keywords: word embeddings, k-mer embedding, dimensionality reduction

Procedia PDF Downloads 114

Authors: Yangze Lan, Ruihua Xv, Feng Zhou, Yijia Shan, Longhao Zhang, Qinghui Xv

Abstract:

Receiving and dispatching trains is an important part of railroad organization, and the risky evaluation of operating personnel is still reflected by scores, lacking further excavation of wrong answers and operating accidents. With natural language processing (NLP) technology, this study extracts the keywords and key phrases of 40 relevant risk events about receiving and dispatching trains and reclassifies the risk events into 8 categories, such as train approach and signal risks, dispatching command risks, and so on. Based on the historical risk data of personnel, the K-Means clustering method is used to classify the risk level of personnel. The result indicates that the high-risk operating personnel need to strengthen the training of train receiving and dispatching operations towards essential trains and abnormal situations.

Keywords: receiving and dispatching trains, natural language processing, risk evaluation, K-means clustering

Procedia PDF Downloads 53

Authors: Claudia Ehrentraut, Osama Ibrahim, Hercules Dalianis

Abstract:

Policy making situations are real-world problems that exhibit complexity in that they are composed of many interrelated problems and issues. To be effective, policies must holistically address the complexity of the situation rather than propose solutions to single problems. Formulating and understanding the situation and its complex dynamics, therefore, is a key to finding holistic solutions. Analysis of text based information on the policy problem, using Natural Language Processing (NLP) and Text analysis techniques, can support modelling of public policy problem situations in a more objective way based on domain experts knowledge and scientific evidence. The objective behind this study is to support modelling of public policy problem situations, using text analysis of verbal descriptions of the problem. We propose a formal methodology for analysis of qualitative data from multiple information sources on a policy problem to construct a causal diagram of the problem. The analysis process aims at identifying key variables, linking them by cause-effect relationships and mapping that structure into a graphical representation that is adequate for designing action alternatives, i.e., policy options. This study describes the outline of an algorithm used to automate the initial step of a larger methodological approach, which is so far done manually. In this initial step, inferences about key variables and their interrelationships are extracted from textual data to support a better problem structuring. A small prototype for this step is also presented.

Keywords: public policy, problem structuring, qualitative analysis, natural language processing, algorithm, inference extraction

Procedia PDF Downloads 568

Authors: Eva L. Sanjuán, Jacinto Martín, M. Isabel Parra, Mario M. Pizarro

Abstract:

In Extreme Value Theory, inference estimation for the parameters of the distribution is made employing a small part of the observation values. When block maxima values are taken, many data are discarded. We developed a new Bayesian inference model to seize all the information provided by the data, introducing informative priors and using the relations between baseline and limit parameters. Firstly, we studied the accuracy of the new model for three baseline distributions that lead to a Gumbel extreme distribution: Exponential, Normal and Gumbel. Secondly, we considered mixtures of Normal variables, to simulate practical situations when data do not adjust to pure distributions, because of perturbations (noise).

Keywords: bayesian inference, extreme value theory, Gumbel distribution, highly informative prior

Procedia PDF Downloads 172

Authors: Aarnav Singh, Jatin Moolchandani

Abstract:

The proposed research work aims to build a query-based AI chatbot that can answer any question related to any topic. A chatbot is software that converses with users via text messages. In the proposed system, we aim to build a chatbot that generates a response based on the user’s query. For this, we use natural language processing to analyze the query and some set of texts to form a concise answer. The texts are obtained through web-scrapping and filtering all the credible sources from a web search. The objective of this project is to provide a chatbot that is able to provide simple and accurate answers without the user having to read through a large number of articles and websites. Creating an AI chatbot that can answer a variety of user questions on a variety of topics is the goal of the proposed research project. This chatbot uses natural language processing to comprehend user inquiries and provides succinct responses by examining a collection of writings that were scraped from the internet. The texts are carefully selected from reliable websites that are found via internet searches. This project aims to provide users with a chatbot that provides clear and precise responses, removing the need to go through several articles and web pages in great detail. In addition to exploring the reasons for their broad acceptance and their usefulness across many industries, this article offers an overview of the interest in chatbots throughout the world.

Keywords: Chatbot, Artificial Intelligence, natural language processing, web scrapping

Procedia PDF Downloads 42

Authors: Yingxu Wang, Jianhua Lu, Jun Peng, Jiawei Zhang

Abstract:

The fundamental demand in contemporary intelligent science towards Autonomous AI (AI*) is the creation of unprecedented formal means of Intelligent Mathematics (IM). It is discovered that natural intelligence is inductively created rather than exhaustively trained. Therefore, IM is a family of algebraic and denotational mathematics encompassing Inference Algebra, Real-Time Process Algebra, Concept Algebra, Semantic Algebra, Visual Frame Algebra, etc., developed in our labs. IM plays indispensable roles in training-free AI* theories and systems beyond traditional empirical data-driven technologies. A set of applications of IM-driven AI* systems will be demonstrated in contemporary intelligence science, AI*, and cognitive computers.

Keywords: intelligence mathematics, foundations of intelligent science, autonomous AI, cognitive computers, inference algebra, real-time process algebra, concept algebra, semantic algebra, applications

Procedia PDF Downloads 36

Authors: Christopher Schwarz, Katrin Riegler, Erwin Zinser

Abstract:

The management of outsourcing relationships between IT service providers and their customers proofs to be a critical issue that has to be stipulated by means of Service Level Agreements (SLAs). Since service requirements differ from customer to customer, SLA content and language structures vary largely, standardized SLA templates may not be used and an automated processing of SLA content is not possible. Hence, SLA management is usually a time-consuming and inefficient manual process. For overcoming these challenges, this paper presents an innovative and ITIL V3-conform approach for automated SLA design and management using controlled natural language in enterprise collaboration portals. The proposed novel concept is based on a self-developed controlled natural language that follows a subject-predicate-object approach to specify well-defined SLA content structures that act as templates for customized contracts and support automated SLA processing. The derived results eventually enable IT service providers to automate several SLA request, approval and negotiation processes by means of workflows and business rules within an enterprise collaboration portal. The illustrated prototypical realization gives evidence of the practical relevance in service-oriented scenarios as well as the high flexibility and adaptability of the presented model. Thus, the prototype enables the automated creation of well defined, customized SLA documents, providing a knowledge representation that is both human understandable and machine processable.

Keywords: automated processing, controlled natural language, knowledge representation, information technology outsourcing, service level management

Procedia PDF Downloads 409

Authors: Yufen Qin

Abstract:

Topic-to-Essay generation is a challenging task in Natural language processing, which aims to generate novel, diverse, and topic-related text based on user input. Previous research has overlooked the generation of articles under the constraints of event elements, resulting in issues such as incomplete event elements and logical inconsistencies in the generated results. To fill this gap, this paper proposes an event-constrained approach for a topic-to-essay generation that enforces the completeness of event elements during the generation process. Additionally, a language model is employed to verify the logical consistency of the generated results. Experimental results demonstrate that the proposed model achieves a better BLEU-2 score and performs better than the baseline in terms of subjective evaluation on a real dataset, indicating its capability to generate higher-quality topic-related text.

Keywords: event element, language model, natural language processing, topic-to-essay generation.

Procedia PDF Downloads 211

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. Computational linguistics is a growing field dealing with such issues of data collection for technological development. 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. Computational analysis on such linguistic data is used to find patterns of misogyny. 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: computational analysis, gendered grammar, misogynistic language, neural networks

Procedia PDF Downloads 97

Authors: Derek Brandon G. Yu, Clyde Vincent O. Pilapil, Christine F. Peña

Abstract:

College students of Cebu province have been indoors since March 2020, and a challenge encountered is the sudden shift from face to face to online learning and with the lack of empirical data on online learning on Higher Education Institutions (HEIs) in the Philippines. Sentiments on face to face and online learning will be collected from University of San Carlos (USC), School of Arts and Sciences (SAS) students regarding Mathematics in the Modern World (MMW), a General Education (GE) course. Natural Language Processing with machine learning algorithms will be used to classify the sentiments of the students. Results of the research study are the themes identified through topic modelling and the overall sentiments of the students in USC SAS

Keywords: natural language processing, online learning, sentiment analysis, topic modelling

Procedia PDF Downloads 218

Authors: Pilar Rey del Castillo

Abstract:

This document describes the building of an average indicator of the general sentiments about the future exposed in the newspapers in Spain. The raw data are collected through the scraping of the Digital Periodical and Newspaper Library website. Basic tools of natural language processing are later applied to the collected information to evaluate the sentiment strength of each word in the texts using a polarized dictionary. The last step consists of summarizing these sentiments to produce daily indices. The results are a first insight into the applicability of these techniques to produce periodic sentiment indicators.

Keywords: natural language processing, periodic indicator, sentiment analysis, web scraping

Procedia PDF Downloads 112

Authors: Neha Kulshreshtha

Abstract:

This paper examines the patterns of 'Mouthing', a non-manual marker, and its distribution in Indian Sign Language (ISL). Linguistic research in Indian Sign Language is an emerging field where much is needed to be done. The little research which has happened focuses on the structure of ISL in terms of physical or manual markers, therefore a study of mouthing patterns would give an insight into the distribution of this particular non-manual marker. Data has been collected with the help of native ISL users through various techniques in which natural signs can be captured, for example, storytelling, informal conversations etc. The aim of the study is to find out the various situations where mouthing is used. Sometimes, the mouthing is not actually the articulation of the word as spoken in the local languages. The paper aims to find out whether the mouthing patterns in ISL are influenced by any local language or they are independent of any influence from the local language or both. Mouthing patterns have been studied in many sign languages and an investigation into ISL will reveal whether it falls in pattern with the other sign languages.

Keywords: Indian sign language, mouthing, non-manual marker, spoken language influence

Procedia PDF Downloads 232