{"title":"AN E-TUTOR TOOL FOR GRAMMATICAL ERROR CORRECTION","authors":"Xiaodong Sun, Yanqin Yin, Huanhuan Lv, Pikun Wang, Hongwei Ma, Dongqiang Yang","doi":"10.33965/icwi2020_202012c022","DOIUrl":"https://doi.org/10.33965/icwi2020_202012c022","url":null,"abstract":"Intelligent language learning tools have evolved into an inevitable aid for ESL/EFL (English as second or foreign language) learners to improve their linguistic skills. By functioning as a machine translation task, automatic grammatical error correction (GEC) has made significant progress with the help of deep neural networks, but its accuracy and coverage rates on different error types have not been fully satisfactory in practice. This paper designs an e-Tutor tool for GEC to help ESL/EFL learners automatically inspect and correct their grammatical errors in writing. One of the core research tasks in GEC is how to improve its generalizability while dealing with more complex error types. In the paper, we propose a novel data augmentation method to add artificial noise to native English corpora during training a neural translation model for GEC. To improve the output quality of GEC, we also design a re-editing module, which mainly consists of a statistical language model, along with a grammatical error detection classifier, in validating each sentence generated by GEC. Experiment results on GEC show that our e-Tutor tool can achieve state-of-the-art performance on the CoNLL-2014 dataset.","PeriodicalId":254527,"journal":{"name":"Proceedings of the 19th International Conference on WWW/Internet","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127320551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Lima, V. Mattos, Raquel F. V. Cunha, Alexandre S. Teixeira, Marcelo Ayres, Luis H. Pascareli, Fernando B. Pires, B. Bonifácio
{"title":"IDENTIFYING DIFFICULTIES IN THE KNOWLEDGE TRANSFER PROCESS IN GLOBAL SOFTWARE: A QUALITATIVE ANALYSIS","authors":"F. Lima, V. Mattos, Raquel F. V. Cunha, Alexandre S. Teixeira, Marcelo Ayres, Luis H. Pascareli, Fernando B. Pires, B. Bonifácio","doi":"10.33965/icwi2020_202012l011","DOIUrl":"https://doi.org/10.33965/icwi2020_202012l011","url":null,"abstract":"Due to increasing demand for new technologies, it is common in software projects to be necessary to incorporate new team members. However, when new hires join a company, they should learn about working process, organization structure, and company corporate culture. Therefore, companies should be adopting strategies to manage and transfer knowledge to better support newcomers. Sidia R&D Institute had to hire new members to increase our Project Leader team, consequence of a massive project demand. As we work in a distributed environment, we use Wiki as an alternative tool for sharing knowledge and for helping newcomers learn about our software development process. However, newer members reported great difficulty during Wiki usage. This paper reports results of a qualitative study aimed to identify the difficulties faced by new team members during wiki usage at Sidia R&D Institute, as well as identify actions that are often adopted to mitigate these difficulties. The study reveals that despite of wiki being important to improve knowledge transfer in Sidia team, newly PLs had difficulties to access wiki information caused by usability issues and lack of adequate knowledge management.","PeriodicalId":254527,"journal":{"name":"Proceedings of the 19th International Conference on WWW/Internet","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129502772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PARTICIPATORY GOVERNABILITY UNDER DEVELOPMENT: THE INSTITUTION OF CITIZEN PARTICIPATION AS THE BASIS FOR THE DESIGN OF THE \"GOVERNMENT AS A PLATFORM\" IN DEVELOPING COUNTRIES","authors":"K. Neverov","doi":"10.33965/icwi2020_202012c019","DOIUrl":"https://doi.org/10.33965/icwi2020_202012c019","url":null,"abstract":"An important point of the government as a platform is coordination with actors traditionally external for public administration (citizens, business) through shared software, data, and collaborative services. Unlike e-government, the focus in digital government is shifting to citizen participation: digital government focuses on services, functions and governance through citizen involvement. The key point here is the interaction of man and technology: the implementation design is a set of principles, methods and norms of interaction between man and technology, that is, a techno-ecological system. The main thesis of the study is the following proposition: the institution of participation is the basis of the design of the “government as a platform” due to the deep foundations of Web 3.0 technology, which encourage participation and have a collaborative nature. Participatory governance is inherent in digital governance. In our study, we strive to demonstrate how the factors determining the classification of countries as developing affect the participatory governability, implemented through the government as a platform. In this study, we adhere to the Lean Government approach.","PeriodicalId":254527,"journal":{"name":"Proceedings of the 19th International Conference on WWW/Internet","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130633640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gabriel Silva, Mário Rodrigues, M. Amorim, Angélica Souza, Marta Dias, Armando J. Pinho
{"title":"ASSESSING JOB MARKET DYNAMICS USING ELK STACK","authors":"Gabriel Silva, Mário Rodrigues, M. Amorim, Angélica Souza, Marta Dias, Armando J. Pinho","doi":"10.33965/icwi2020_202012l012","DOIUrl":"https://doi.org/10.33965/icwi2020_202012l012","url":null,"abstract":"The adoption of digital technologies promises to accelerate the transformation and the agility of processes, work activities and revenue models. Yet, the promised gains come together with dramatic needs for qualified professionals who can effectively leverage the technology potential. Job contexts are being reshaped as new models for the interaction and integration of humans and technologies take shape. To increase the readiness of the job market in this fast-changing context it is important that all stakeholders – companies, professionals, policy makers – are aware of the job market dynamics and needs. This can be observed from the collection of job announcements, but its high volume requires effective tools for analyzing and simplifying it in order to draw timely and correct conclusions. ELK stack was used for dealing with the high volume of job announcements. ELK is a stable platform that can manage large quantities of data and the Kibana layer enables to rapidly explore data and create visualization dashboards. As job announcements have distinct formulations for similar roles, depending on the hiring company, this raises the necessity of establishing a common ground for comparing the job descriptions. In this work were mapped job descriptions to ESCO occupations. ESCO is an ontology published by the European Union and its occupations are job positions. Results show that the ELK stack is a suitable tool for providing a visual interpretation on the job market dynamics. Moreover, the first experiments using natural language processing techniques and machine learning algorithms revealed an accuracy over 0.9 in mapping job descriptions to ESCO occupations. This result is very promising and shows that ESCO a good candidate as common ground to enable comparison of job market dynamics for distinct environments.","PeriodicalId":254527,"journal":{"name":"Proceedings of the 19th International Conference on WWW/Internet","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134028514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"USING SEMANTIC RELATIONSHIPS TO ENHANCE NEURAL WORD EMBEDDINGS","authors":"","doi":"10.33965/icwi2020_202012c020","DOIUrl":"https://doi.org/10.33965/icwi2020_202012c020","url":null,"abstract":"","PeriodicalId":254527,"journal":{"name":"Proceedings of the 19th International Conference on WWW/Internet","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116721363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}