DOCSLIB.ORG

Department of Computer Engineering

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Department of Computer Engineering DEPARTMENT OF COMPUTER ENGINEERING DEPARTMENT OF COMPUTER ENGINEERING Vision To create an Engineer, receptive to the changing demands of the global market. Mission To provide technically competent professionals in service to Nation. To prepare graduates to respond to the needs of dynamically changing technology. Program Education Objectives(PEOs) PEO1: To prepare graduates to work productively as successful Computer professionals. PEO2: To prepare graduates with latest skills in the field of technologies supplemented with practical orientation to face challenges of modern computing industry. PEO3: To provide environment that fosters professional growth, communication skill, team work, life-long learning skill and ability to create awareness in society about applications of technology. Program Specific Outcomes (PSOs) PSO1 Problem Solving and Programming Skills: Graduates will be able to apply computational techniques and complete individual practical experiences in a variety of programming languages and situations. PSO2 Professional Skills: Graduates will be able to design and develop efficient and effective software by following standard software engineering principles. PSO3 Successful Career: Graduates will be able to become entrepreneur and to pursue higher studies / career in IT industries. DEPARTMENT OF COMPUTER ENGINEERING Program Outcomes (POs) Graduates will be able to 1. Apply the knowledge of mathematics, science, engineering fundamentals, and an engineering specialization to the solution of complex engineering problems. [Engineering knowledge] 2. Identify, formulate, research literature, and analyse complex engineering problems reaching substantiated conclusions using first principles of mathematics, natural sciences, and engineering sciences. [Problem analysis] 3. Design solutions for complex engineering problems and design system components or processes that meet the specified needs with appropriate consideration for the public health and safety, and the cultural, societal, and environmental considerations. [Design/development of solutions] 4. Use research-based knowledge and research methods including design of experiments, analysis and interpretation of data, and synthesis of the information to provide valid conclusions. [Conduct investigations of complex problems] 5. Create, select, and apply appropriate techniques, resources, and modern engineering and IT tools including prediction and modelling to complex engineering activities with an understanding of the limitations. [Modern tool usage] 6. Apply reasoning informed by the contextual knowledge to assess societal, health, safety, legal and cultural issues and the consequent responsibilities relevant to the professional engineering practice. [The engineer and society] 7. Understand the impact of the professional engineering solutions in societal and environmental contexts, and demonstrate the knowledge of, and need for sustainable development. [Environment and sustainability] 8. Apply ethical principles and commit to professional ethics and responsibilities and norms of the engineering practice. [Ethics] DEPARTMENT OF COMPUTER ENGINEERING 9. Function effectively as an individual, and as a member or leader in diverse teams, and in multidisciplinary settings. [Individual and team work] 10. Communicate effectively on complex engineering activities with the engineering community and with society at large, such as, being able to comprehend and write effective reports and design documentation, make effective presentations, and give and receive clear instructions. [Communication] 11. Demonstrate knowledge and understanding of the engineering and management principles and apply these to one’s own work, as a member and leader in a team, to manage projects and in multidisciplinary environments. [Project management and finance] 12. Recognize the need for, and have the preparation and ability to engage in independent and life-long learning in the broadest context of technological change. [Life-long learning] DEPARTMENT OF COMPUTER ENGINEERING Editorial Team Faculty Coordinator: S.P.Pimpalkar I am joyful to introduce you to the departmental technical magazine. The intention of this magazine is to supply chance and platform for the younger college students to show off their talent, which can even be recommended to any or all others to raise their technical knowledge. I agree with that this journal serves the purpose. Student Coordinator: Prasanna Vidhate Kajal Sonawane DEPARTMENT OF COMPUTER ENGINEERING Objective behind Technical Magazine Department of Computer Engineering is very happy and proud to publish technical magazine of year 2018-19. We have gathered technical articles from our students worked as intern in Tech Mahindra IT industry. These articles gives guidelines to students regarding what is expected in IT industry and how various technologies are applied for the projects in IT industry. Department has set objective to bring technical competency among the students. Department is taking efforts for the same since second year of these students. Department arranges various expert lectures, workshops, industrial visits, learning contents beyond syllabus for the students. All these activities are planned to make students aware of current need of IT industry. Outcome of these efforts is reflected through their final year projects, placement and admission to higher studies. We had collected project details from our students who worked in Tech Mahindra as intern. We are sharing experience technical work of these students with our students through this magazine. Our objective behind sharing this information is to motivate students and to create awareness among them about current need in IT industry. Coordinator HOD S.P.Pimpalkar Dr. S.N.Zaware DEPARTMENT OF COMPUTER ENGINEERING INDEX Sr.No Content Page No. 1 About Tech Mahindra Limited 1 2 About Maker’s Lab 2 3 Student’s work experience 3 4 Dynamic HTML code generation 4 5 Translation of English words from a German-English 6 bi-lingual text for Natural Language Processing 6 Japanese NLP MeCab Tool 12 16 7 Counter Raffle unity 3D software 19 8 Augmented Football Stadium Application 22 9 Watson Chatbot DEPARTMENT OF COMPUTER ENGINEERING 1. About Tech Mahindra Limited Tech Mahindra Limited is an Indian multinational provider of information technology (IT), networking technology solutions and Business Process Outsourcing (BPO) to various industry verticals and horizontals. Tech Mahindra represents connected world, offering innovative and customer-centric information technology experiences, enabling Enterprises, Associates and the society to RiseTM . It is a 4.35 billion company with 112,000 + professionals across 90 countries, helping over 903 global customers including fortune 500 companies. Tech Mahindra’s convergent, digital, design experiences, innovation platforms and reusable assets connect across a number of technologies to deliver tangible business value and experiences to our stakeholders. Tech Mahindra is amongst the Fab50 companies in Asia (Forbes 2016 list). Tech Mahindra is a part of USD 19 billion Mahindra Group that employs more than 2 lakh people in over 100 countries. The Group operates in the key industries that drive economic growth, enjoying a leadership position in tractors, utility vehicles, after market, information technology and vacation ownership. Vision Company’s vision is to be among the top three leaders in its chosen market segments while fostering innovation and inclusion. It will consistently achieve top quartile growth by contributing to customer’s success, by enabling employees to realize their potential and by creating value for all stake holders. 1 Department of Computer Engineering-Technical Magazine 2018-2019 DEPARTMENT OF COMPUTER ENGINEERING 2. About Maker’s Lab 2 Department of Computer Engineering-Technical Magazine 2018-2019 DEPARTMENT OF COMPUTER ENGINEERING 3. Student’s Work Experience Maker’s lab is the research and development area of tech Mahindra; It is under the Leadership of my guide, Mr. Nikhil Malhotra who is the global head. Maker’s lab has Branches in Chennai, Bangalore, Hyderabad, Pune and also Dallas in USA and Ipswich in England and with more to come. They specialize in the modern trends in information Technology such as Machine Learning, Artificial Intelligence, Internet of things, Augmented and Virtual Reality. Although I am under the guidance of Mr. Nikhil Malhotra, I am working under Mr. Saurabh Shaligram, who have helped me in the most Important project. My mentor also likes my work and is a helpful figure, giving thoughtful advice on various fields and encouraged me to also take a look at machine learning as it is helpful. So, in general, Maker’s lab is an amazing place to be there to work and it is also a great Place for industrial visits due to the various products they have to showcase. 3 Department of Computer Engineering-Technical Magazine 2018-2019 DEPARTMENT OF COMPUTER ENGINEERING 4. Dynamic HTML Code Generation Pratiksha Jatti Arbaaz Shaikh Sujay Patil Isha Doshi The project is based on the concepts of Convolutional Neural Network(Deep Learning).It is a class of deep neural network most commonly applied for analysing visual imagery. A convolutional neural network consists of an input and an output layer, as well as multiple hidden layers. The hidden layers of a CNN typically consist of convolutional layers, RELU layer i.e. activation. Task Definition The project is aimed at creating a web page in Hyper Text Mark-up Language using Machine Learning.
Load more

Recommended publications
  • Mysql NDB Cluster 7.5.16 (And Later)
    Licensing Information User Manual MySQL NDB Cluster 7.5.16 (and later) Table of Contents Licensing Information .......................................................................................................................... 2 Licenses for Third-Party Components .................................................................................................. 3 ANTLR 3 .................................................................................................................................... 3 argparse .................................................................................................................................... 4 AWS SDK for C++ ..................................................................................................................... 5 Boost Library ............................................................................................................................ 10 Corosync .................................................................................................................................. 11 Cyrus SASL ............................................................................................................................. 11 dtoa.c ....................................................................................................................................... 12 Editline Library (libedit) ............................................................................................................. 12 Facebook Fast Checksum Patch ..............................................................................................
    [Show full text]
  • Konlpy Documentation 출시 0.4.1
    KoNLPy Documentation 출시 0.4.1 Lucy Park 2015D 02월 25| Contents 1 Standing on the shoulders of giants2 2 License 3 3 Contribute 4 4 Getting started 5 4.1 What is NLP?............................................5 4.2 What do I need to get started?....................................5 5 User guide 6 5.1 Installation..............................................6 5.2 Morphological analysis and POS tagging..............................7 5.3 Data.................................................. 10 5.4 Examples............................................... 11 5.5 Running tests............................................. 23 5.6 References.............................................. 23 6 API 26 6.1 konlpy Package............................................ 26 7 Indices and tables 34 Python ¨È ©] 35 i KoNLPy Documentation, 출시 0.4.1 (https://travis-ci.org/konlpy/konlpy) (https://readthedocs.org/projects/konlpy/?badge=latest) KoNLPy (pro- nounced “ko en el PIE”) is a Python package for natural language processing (NLP) of the Korean language. For installation directions, see here (page 6). For users new to NLP, go to Getting started (page 5). For step-by-step instructions, follow the User guide (page 6). For specific descriptions of each module, go see the API (page 26) documents. >>> from konlpy.tag import Kkma >>> from konlpy.utils import pprint >>> kkma= Kkma() >>> pprint(kkma.sentences(u’$, HUX8요. 반갑습니다.’)) [$, HUX8요.., 반갑습니다.] >>> pprint(kkma.nouns(u’È8t나 tX¬m@ C헙 t슈 ¸래커Ð ¨¨주8요.’)) [È8, tX, tX¬m, ¬m, C헙, t슈, ¸래커] >>> pprint(kkma.pos(u’$X보고는 실행X½, Ð러T8지@h께 $명D \대\Á8히!^^’)) [($X, NNG), (보고, NNG), (는, JX), (실행, NNG), (X½, NNG), (,, SP), (Ð러, NNG), (T8지, NNG), (@, JKM), (h께, MAG), ($명, NNG), (D, JKO), (\대\, NNG), (Á8히, MAG), (!, SF), (^^, EMO)] Contents 1 CHAPTER 1 Standing on the shoulders of giants Korean, the 13th most widely spoken language in the world (http://www.koreatimes.co.kr/www/news/nation/2014/05/116_157214.html), is a beautiful, yet complex language.
    [Show full text]
  • Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation
    Learning to Generate Pseudo-code from Source Code using Statistical Machine Translation Yusuke Oda, Hiroyuki Fudaba, Graham Neubig, Hideaki Hata, Sakriani Sakti, Tomoki Toda, and Satoshi Nakamura Graduate School of Information Science, Nara Institute of Science and Technology 8916-5 Takayama, Ikoma, Nara 630-0192, Japan foda.yusuke.on9, fudaba.hiroyuki.ev6, neubig, hata, ssakti, tomoki, [email protected] Abstract—Pseudo-code written in natural language can aid comprehension of beginners because it explicitly describes the comprehension of source code in unfamiliar programming what the program is doing, but is more readable than an languages. However, the great majority of source code has no unfamiliar programming language. corresponding pseudo-code, because pseudo-code is redundant and laborious to create. If pseudo-code could be generated Fig. 1 shows an example of Python source code, and En- automatically and instantly from given source code, we could glish pseudo-code that describes each corresponding statement allow for on-demand production of pseudo-code without human in the source code.1 If the reader is a beginner at Python effort. In this paper, we propose a method to automatically (or a beginner at programming itself), the left side of Fig. generate pseudo-code from source code, specifically adopting the 1 may be difficult to understand. On the other hand, the statistical machine translation (SMT) framework. SMT, which was originally designed to translate between two natural lan- right side of the figure can be easily understood by most guages, allows us to automatically learn the relationship between English speakers, and we can also learn how to write specific source code/pseudo-code pairs, making it possible to create a operations in Python (e.g.
    [Show full text]
  • “Computer Programming IV” As Capstone Design and Laboratory Attachment Shoichi Yokoyama† Yamagata University, Yonezawa, Japan
    Journal of Engineering Education Research Vol. 15, No. 5, pp. 31~35, September, 2012 “Computer Programming IV” as Capstone Design and Laboratory Attachment Shoichi Yokoyama† Yamagata University, Yonezawa, Japan ABSTRACT A new obligatory subject, Computer Programming IV, is organized in the Department of Informatics, Faculty of Engineering, Yamagata University. The purposes of the subject are as follows: (1) Attachment to each laboratory for bachelor thesis was usually at the initial stage of the student’s fourth academic year. This subject actually moves up the attachment because students are tentatively attached to a laboratory for this subject. The interval to complete their bachelor thesis is extended by half a year. (2) In each laboratory, students cooperate with each other to complete their project. The project becomes capstone design which JABEE (Japan Accreditation Board for Engineering Education) is recently emphasizing. We not only explain the introduction of this subject, but also report some case studies. Keywords: Engineering education, Capstone design, Laboratory attachment, Project, JABEE I. Introduction 1) third academic year, so that students first took the subject in 2009. The detailed plan created before this first use is The education program of the Department of Informatics, described in [2]. Faculty of Engineering, Yamagata University (YUDI) was The present paper describes the syllabus and proceeds accredited in 2003 by Japan Accreditation Board for to describe case studies of some laboratories. We explain Engineering Education (JABEE) [1], the second to be three years of results. accredited for information engineering. Through the in- Computer Programming IV has the following two purposes: termediate examination in 2005, the program was re- accredited in 2008 for the 2009 to 2014 period.
    [Show full text]
  • Mysql Installation Guide Abstract
    MySQL Installation Guide Abstract This is the MySQL Installation Guide from the MySQL 5.7 Reference Manual. For legal information, see the Legal Notices. For help with using MySQL, please visit the MySQL Forums, where you can discuss your issues with other MySQL users. Document generated on: 2021-10-06 (revision: 70984) Table of Contents Preface and Legal Notices ............................................................................................................ v 1 Installing and Upgrading MySQL ................................................................................................ 1 2 General Installation Guidance .................................................................................................... 3 2.1 Supported Platforms ....................................................................................................... 3 2.2 Which MySQL Version and Distribution to Install .............................................................. 3 2.3 How to Get MySQL ........................................................................................................ 4 2.4 Verifying Package Integrity Using MD5 Checksums or GnuPG .......................................... 5 2.4.1 Verifying the MD5 Checksum ............................................................................... 5 2.4.2 Signature Checking Using GnuPG ........................................................................ 5 2.4.3 Signature Checking Using Gpg4win for Windows ................................................. 13 2.4.4
    [Show full text]
  • ML-Ask: Open Source Affect Analysis Software for Textual Input In
    Ptaszynski, M et al 2017 ML-Ask: Open Source Affect Analysis Software Journal of for Textual Input in Japanese. Journal of Open Research Software, 5: 16, open research software DOI: https://doi.org/10.5334/jors.149 SOFTWARE METAPAPER ML-Ask: Open Source Affect Analysis Software for Textual Input in Japanese Michal Ptaszynski1,2, Pawel Dybala3,4, Rafal Rzepka5,6, Kenji Araki5,6 and Fumito Masui2,7 1 Software Development, Open Source Version Development, JP 2 Department of Computer Science, Kitami Institute of Technology, Kitami, JP 3 Software Development, PL 4 Institute Of Middle and Far Eastern Studies, Faculty of International and Political Studies, Jagiellonian University, Kraków, PL 5 Software Development Supervision, JP 6 Language Media Laboratory, Graduate School of Information Science and Technology, Hokkaido University, Sapporo, JP 7 Open Source Version Development Supervision, JP Corresponding author: Michal Ptaszynski ([email protected]) We present ML-Ask – the first Open Source Affect Analysis system for textual input in Japanese. ML-Ask analyses the contents of an input (e.g., a sentence) and annotates it with information regarding the contained general emotive expressions, specific emotional words, valence-activation dimensions of overall expressed affect, and particular emotion types expressed with their respective expressions. ML-Ask also incorporates the Contextual Valence Shifters model for handling negation in sentences to deal with grammatically expressible shifts in the conveyed valence. The system, designed to work mainly under Linux and MacOS, can be used for research on, or applying the techniques of Affect Analysis within the framework Japanese language. It can also be used as an experimental baseline for specific research in Affect Analysis, and as a practical tool for written contents annotation.
    [Show full text]
  • Release 0.5.1 Lucy Park
    KoNLPy Documentation Release 0.5.1 Lucy Park Aug 03, 2018 Contents 1 Standing on the shoulders of giants2 2 License 3 3 Contribute 4 4 Getting started 5 4.1 What is NLP?............................................5 4.2 What do I need to get started?....................................5 5 User guide 7 5.1 Installation..............................................7 5.2 Morphological analysis and POS tagging.............................. 10 5.3 Data.................................................. 13 5.4 Examples............................................... 14 5.5 Running tests............................................. 28 5.6 References.............................................. 28 6 API 32 6.1 konlpy Package............................................ 32 7 Indices and tables 42 Python Module Index 43 i KoNLPy Documentation, Release 0.5.1 (https://travis-ci.org/konlpy/konlpy) (https://readthedocs.org/projects/konlpy/?badge=latest) KoNLPy (pro- nounced “ko en el PIE”) is a Python package for natural language processing (NLP) of the Korean language. For installation directions, see here (page 7). For users new to NLP, go to Getting started (page 5). For step-by-step instructions, follow the User guide (page 7). For specific descriptions of each module, go see the API (page 32) documents. >>> from konlpy.tag import Kkma >>> from konlpy.utils import pprint >>> kkma= Kkma() >>> pprint(kkma.sentences(u'$, HUX8요. 반갑습니다.')) [$, HUX8요.., 반갑습니다.] >>> pprint(kkma.nouns(u'È8t나 tX¬m@ C헙 t슈 ¸래커Ð ¨¨주8요.')) [È8, tX, tX¬m, ¬m, C헙, t슈, ¸래커] >>> pprint(kkma.pos(u'$X보고는 실행X½, Ð러T8지@h께 $명D \대\Á8히!^^')) [($X, NNG), (보고, NNG), (는, JX), (실행, NNG), (X½, NNG), (,, SP), (Ð러, NNG), (T8지, NNG), (@, JKM), (h께, MAG), ($명, NNG), (D, JKO), (\대\, NNG), (Á8히, MAG), (!, SF), (^^, EMO)] Contents 1 CHAPTER 1 Standing on the shoulders of giants Korean, the 13th most widely spoken language in the world (http://www.koreatimes.co.kr/www/news/nation/2014/05/116_157214.html), is a beautiful, yet complex language.
    [Show full text]
  • Latest) Konlpy (Pro- Nounced “Ko En El PIE”) Is a Python Package for Natural Language Processing (NLP) of the Korean Language
    KoNLPy Documentation Release 0.5.2 Lucy Park Dec 03, 2019 Contents 1 Standing on the shoulders of giants2 2 License 3 3 Contribute 4 4 Getting started 5 4.1 What is NLP?............................................5 4.2 What do I need to get started?....................................5 5 User guide 7 5.1 Installation..............................................7 5.2 Morphological analysis and POS tagging.............................. 10 5.3 Data.................................................. 13 5.4 Examples............................................... 15 5.5 Running tests............................................. 29 5.6 References.............................................. 29 6 API 33 6.1 konlpy Package............................................ 33 7 Indices and tables 44 Python Module Index 45 Index 46 i KoNLPy Documentation, Release 0.5.2 (https://travis-ci.org/konlpy/konlpy) (https://readthedocs.org/projects/konlpy/?badge=latest) KoNLPy (pro- nounced “ko en el PIE”) is a Python package for natural language processing (NLP) of the Korean language. For installation directions, see here (page 7). For users new to NLP, go to Getting started (page 5). For step-by-step instructions, follow the User guide (page 7). For specific descriptions of each module, go see the API (page 33) documents. >>> from konlpy.tag import Kkma >>> from konlpy.utils import pprint >>> kkma= Kkma() >>> pprint(kkma.sentences(u'$, HUX8요. 반갑습니다.')) [$, HUX8요.., 반갑습니다.] >>> pprint(kkma.nouns(u'È8t나 tX¬m@ C헙 t슈 ¸래커Ð ¨¨주8요.')) [È8, tX, tX¬m, ¬m, C헙, t슈, ¸래커] >>> pprint(kkma.pos(u'$X보고는 실행X½, Ð러T8지@h께 $명D \대\Á8히!^^')) [($X, NNG), (보고, NNG), (는, JX), (실행, NNG), (X½, NNG), (,, SP), (Ð러, NNG), (T8지, NNG), (@, JKM), (h께, MAG), ($명, NNG), (D, JKO), (\대\, NNG), (Á8히, MAG), (!, SF), (^^, EMO)] Contents 1 CHAPTER 1 Standing on the shoulders of giants Korean, the 13th most widely spoken language in the world (http://www.koreatimes.co.kr/www/news/nation/2014/05/116_157214.html), is a beautiful, yet complex language.
    [Show full text]
  • Comparison of Korean Preprocessing Performance According to Tokenizer in NMT Transformer Model
    Journal of Advances in Information Technology Vol. 11, No. 4, November 2020 Comparison of Korean Preprocessing Performance according to Tokenizer in NMT Transformer Model Geumcheol Kim and Sang-Hong Lee Department of Computer Science & Engineering, Anyang University, Anyang-si, Republic of Korea Email: [email protected], [email protected] Abstract—Mechanical translation using neural networks in greatly depending on the characteristics of each language. natural language processing is making rapid progress. With Recently, we are using tokenizer based on morphological the development of natural language processing model and analysis that identifies grammatical structures such as tokenizer, accurate translation is becoming possible. In this root, prefix, and verb, and Tokenizer based On Byte Pair paper, we will create a transformer model that shows high Encoding (BPE), a data compression technique that can performance recently and compare the performance of English Korean according to tokenizer. We made a reduce problems (Out of Vocabulary, OOV) that do not traditional neural network-based Neural Machine exist in learning. Translation (NMT) model using a transformer and Because the performance of these tokenizer varies compared the Korean translation results according to the from language to language, it seems necessary to find tokenizer. The Byte Pair Encoding (BPE)-based Tokenizer tokenizer that fits the Korean language. The composition showed a small vocabulary size and a fast learning speed, of this paper aims to introduce the Transformer model but due to the nature of Korean, the translation result was and create the English-Korean NMT model to enhance not good. The morphological analysis-based Tokenizer the performance of Korean translation by comparing the showed that the parallel corpus data is large and the performance according to tokenizer.
    [Show full text]
  • Department of Computer Engineering
    Department of Computer Engineering Objective behind Technical Magazine Department of Computer Engineering is very happy and proud to publish technical magazine of year 2018-19. We have gathered technical articles from our students worked as intern in Tech Mahindra IT industry. These articles gives guidelines to students regarding what is expected in IT industry and how various technologies are applied for the projects in IT industry. Department has set objective to bring technical competency among the students. Department is taking efforts for the same since second year of these students. Department arranges various expert lectures,workshops,industrial visits,learning contents beyond syllabus for the students. All these activities are planned to make students aware of current need of IT industry. Outcome of these efforts is reflected through their final year projects ,placement and admission to higher studies. We had collected project details from our studenst who worked in Tech Mahindra as intern . We are sharing experience technical work of these students with our students through this magazine. Our objective behind sharing this information is to motivate students and to create awareness among them about current need in IT industy. Coordinator HOD S.P.Pimpalkar S.N.Zaware Contents 1. About Tech Mahindra Limited 2. About Maker‟s Lab 3. Student’s work experience 4. Dynamic HTML code generation Pratiksha Jatti Arbaaz Shaikh Sujay Patil Isha Doshi 5. Translation of English words from a German-English bi-lingual text for Natural Language Processing Gautami Mudaliar Tejasvi Gadakh 6. Japanese NLP MeCab Tool Jincy Biju Mrinal Bhangale 7. Counter Raffle Unity3D Software Jaymala Pawar Smita Muke Parv Javheri 8.
    [Show full text]
  • Release Notes for Oracle Linux 8.2
    Oracle® Linux 8 Release Notes for Oracle Linux 8.2 F31299-14 August 2021 Oracle Legal Notices Copyright © 2020, 2021, Oracle and/or its affiliates. This software and related documentation are provided under a license agreement containing restrictions on use and disclosure and are protected by intellectual property laws. Except as expressly permitted in your license agreement or allowed by law, you may not use, copy, reproduce, translate, broadcast, modify, license, transmit, distribute, exhibit, perform, publish, or display any part, in any form, or by any means. Reverse engineering, disassembly, or decompilation of this software, unless required by law for interoperability, is prohibited. The information contained herein is subject to change without notice and is not warranted to be error-free. If you find any errors, please report them to us in writing. If this is software or related documentation that is delivered to the U.S. Government or anyone licensing it on behalf of the U.S. Government, then the following notice is applicable: U.S. GOVERNMENT END USERS: Oracle programs (including any operating system, integrated software, any programs embedded, installed or activated on delivered hardware, and modifications of such programs) and Oracle computer documentation or other Oracle data delivered to or accessed by U.S. Government end users are "commercial computer software" or "commercial computer software documentation" pursuant to the applicable Federal Acquisition Regulation and agency-specific supplemental regulations. As such, the use, reproduction, duplication, release, display, disclosure, modification, preparation of derivative works, and/or adaptation of i) Oracle programs (including any operating system, integrated software, any programs embedded, installed or activated on delivered hardware, and modifications of such programs), ii) Oracle computer documentation and/or iii) other Oracle data, is subject to the rights and limitations specified in the license contained in the applicable contract.
    [Show full text]
  • Arxiv:2003.06651V1 [Cs.CL] 14 Mar 2020
    Word Sense Disambiguation for 158 Languages using Word Embeddings Only Varvara Logacheva1, Denis Teslenko2, Artem Shelmanov1, Steffen Remus3, Dmitry Ustalov4?, Andrey Kutuzov5, Ekaterina Artemova6, Chris Biemann3, Simone Paolo Ponzetto4, Alexander Panchenko1 1Skolkovo Institute of Science and Technology, Moscow, Russia [email protected] 2Ural Federal University, Yekaterinburg, Russia 3Universität Hamburg, Hamburg, Germany 4Universität Mannheim, Mannheim, Germany 5University of Oslo, Oslo, Norway 6Higher School of Economics, Moscow, Russia Abstract Disambiguation of word senses in context is easy for humans, but is a major challenge for automatic approaches. Sophisticated supervised and knowledge-based models were developed to solve this task. However, (i) the inherent Zipfian distribution of supervised training instances for a given word and/or (ii) the quality of linguistic knowledge representations motivate the development of completely unsupervised and knowledge-free approaches to word sense disambiguation (WSD). They are particularly useful for under-resourced languages which do not have any resources for building either supervised and/or knowledge-based models. In this paper, we present a method that takes as input a standard pre-trained word embedding model and induces a fully-fledged word sense inventory, which can be used for disambiguation in context. We use this method to induce a collection of sense inventories for 158 languages on the basis of the original pre-trained fastText word embeddings by Grave et al. (2018), enabling WSD in these languages. Models and system are available online. Keywords: word sense induction, word sense disambiguation, word embeddings, sense embeddings, graph clustering 1. Introduction biguation needs knowledge-rich approaches. There are many polysemous words in virtually any lan- We tackle this problem by suggesting a method of post- guage.
    [Show full text]